# unlearn.health

> AI-optimized mirror of unlearn.health containing 48 pages totalling 38,057 words of clean markdown content, structured data, and semantic HTML. Original source: https://unlearn.health/. Last updated: 2026-06-13T22:47:33.830Z.

Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG).

## Homepage

- [Driving clarity in clinical development](/content/site-root.html): Discover how Unlearn uses AI to create digital twins of clinical trial participants, streamlining clinical development and enabling confident decision-making. (933 words)

## Articles & Blog Posts

- [Blog](/content/blog/success-is-never-a-straight-line-reflecting-on-our-ema-draft-qualification-opinion.html): Last week, we reached an historic milestone with the EMA’s release of a draft qualification opinion on our 3-step PROCOVA™ procedure. (1,420 words)
- [Blog](/content/blog/the-best-15-minutes-youll-spend-on-clinical-trials-today.html): What if you could see into the future of every patient in your trial?‍ At the 2025 “Digital Breakthrough for Pharma” Summit hosted by Bristol Myers Squibb, Unlearn’s co-founder and machine learning scientist, Aaron Smith, took the stage to explain exactly how that vision is now a reality. (569 words)
- [Blog](/content/blog/why-the-fdas-new-ai-guidelines-matter-for-clinical-research.html): The U.S. Food and Drug Administration (FDA) recently proposed a framework to evaluate the credibility of artificial intelligence (AI) used in drug development—a move that could reshape how clinical trials are designed and run. (727 words)
- [Prathyusha Duraibabu](/content/team/prathyusha-duraibabu/index.html): Meet Unlearn's Chief Financial & Operating Officer, Prathyusha Duraibabu, a strategic leader with decades of experience building and scaling companies from early commercialization through public markets. (359 words)
- [Andrew Stelzer](/content/team/andrew-stelzer/index.html): Meet Unlearn Head of Business Development Andrew Stelzer, a business development expert in the biotechnology and pharmaceutical industries. (213 words)
- [Aaron Smith](/content/team/aaron-smith/index.html): Meet Unlearn founder Aaron Smith, a mathematician with research interests in computer vision, machine learning, physics, and geometry. (190 words)
- [Steve Herne](/content/team/steve-herne/index.html): Meet Unlearn's CEO, Steve Herne, a distinguished professional with 25+ years of experience in the pharmaceutical research & development industry. (219 words)
- [Krates Ng](/content/team/krates-ng/index.html): Meet Unlearn's Chief Technology Officer, Krates Ng, a seasoned technology leader with deep experience in enterprise software, focused on building and scaling high-performing product and engineering teams in healthcare and AI. (213 words)
- [blog/why-predicting-outcomes-has-become-the-hardest-part-of-oncology-trial-design.html](/content/blog/why-predicting-outcomes-has-become-the-hardest-part-of-oncology-trial-design.html) (1 words)
- [Blog](/content/blog/how-unlearn-embeds-into-clinical-trial-teams/index.html): Unlearn bridges the gap between innovation and execution by embedding AI into trials with cross-functional support that directly incorporates into your team’s workflows. Here’s how. (823 words)
- [Blog](/content/blog/how-unlearn-builds-trustworthy-ai-from-messy-clinical-data.html): Quality data is at the heart of any high-performing AI model, but wrangling data into a modeling-ready state can be challenging and time-consuming. (959 words)
- [Blog](/content/blog/empowering-biostatistics-teams-with-ai-that-works-for-them.html): Biostatistics teams are the foundation of every successful trial. Their analyses determine whether studies are credible, reproducible, and regulator-ready. They’re also the ones carrying a growing burden: balancing limited sample sizes with the demand for higher precision, navigating incomplete or messy datasets, and working under increasing pressure to deliver results faster. (730 words)
- [Blog](/content/blog/real-trials-real-impact-q2-at-unlearn/index.html): One of the most rewarding parts of my role is working alongside teams excited about using AI to make clinical development more efficient and, ultimately, better for patients. This quarter, I’m especially proud of how we brought that vision to life, advancing the real-world use of AI-generated digital twins in clinical trials through bold collaboration. (864 words)
- [Blog](/content/blog/driving-clinical-trial-innovation-with-our-partners-q3-at-unlearn.html): Clinical trials have always been complex, requiring input and expertise across biostatistics, regulatory, clinical, and operations teams, among others. At Unlearn, we’re innovating to bring those pieces together so programs can move forward faster, with fewer risks and better-informed decisions. (828 words)
- [Blog](/content/blog/2025-proving-how-purpose-built-ai-moves-the-needle-in-clinical-development.html): Clinical development has never been more complex or more expensive. But with that complexity comes opportunity for teams willing to rethink how evidence is generated, how decisions are made, and how quickly new therapies can move forward. We’re not here to make trials 5% more efficient. We’re here to help teams design smarter studies, align more quickly, and make decisions with greater clarity and confidence. (820 words)
- [Blog](/content/blog/unlearning-the-old-ways-reflections-from-the-fda-ctti-workshop.html): The transition to a model-centric future is inevitable. The question is no longer if AI will transform drug development, but how quickly we are willing to unlearn our old habits to make it happen. (872 words)
- [Blog](/content/blog/whats-next-in-ad-research-highlights-and-lessons-from-aaic-2025.html): AAIC 2025 showcased an Alzheimer’s research community entering a new era. Sponsors are advancing earlier-phase trials, exploring a wider range of treatment modalities, and embracing biomarker-driven strategies for more targeted intervention. Yet while the science is accelerating, trial infrastructure is struggling to keep pace. (774 words)
- [Blog](/content/blog/derisking-clinical-development-with-digital-twins-key-takeaways-from-the-mrct-center-webinar-series.html): Unlearn's Machine Learning Scientist, Daniele Bertolini, recently partnered with the Multi-Regional Clinical Trial Center (MRCT Center) of Brigham and Women's Hospital and Harvard to host a two-part webinar series on leveraging AI-generated digital twins of study participants and synthetic data in clinical development. (618 words)
- [Blog](/content/blog/how-unlearn-boosts-trial-power-using-the-fdas-ai-framework.html): We’ve been pioneering the use of AI in clinical trials for nearly a decade while earning EMA qualification for our PROCOVA method, holding successful Type C meetings with the FDA, and collaborating with regulators to define best practices for AI credibility. (1,096 words)
- [privacy/index.html](/content/privacy/index.html) (1 words)
- [terms/index.html](/content/terms/index.html) (1 words)
- [Data Acknowledgements](/content/data-acknowledgements/index.html): Explore Unlearn.AI's Data Acknowledgments to see how diverse data sources contribute to our groundbreaking AI research and Digital Twin Generators for clinical trials. (4,768 words)
- [Jon Walsh](/content/team/jon-walsh/index.html): Meet Unlearn founder & Chief Scientific Officer Jon Walsh, a physicist whose research interests focus on data science and machine learning. (225 words)
- [Harnessing data, AI, and digital twins to transform clinical development](/content/about/index.html): Unlearn pioneers AI-driven solutions for clinical trials with digital twins of trial participants that streamline clinical development and will eliminate trial and error in medicine tomorrow. (296 words)
- [Press](/content/press/index.html): Stay updated with Unlearn's latest news and announcements. Explore press releases, media coverage, and insights on our advancements in AI-powered solutions for clinical trials. (354 words)
- [Join us at the frontier  of AI in medicine](/content/careers/index.html): Join Unlearn and shape the future of AI in clinical trials. Explore career opportunities with the leader in digital twin technology for clinical development., OUR MISSION AND VISION

Unlearn exists to transform clinical development by making every trial smarter. We harness data, AI, and digital twins to enable faster, more robust studies that bring life-saving treatments to patients faster. This mission drives everything we do as we partner with biopharmaceutical companies to redesign how clinical trials are planned, run, and analyzed.

We are defining the future of clinical development with unmatched scientific credibility, replacing uncertainty with AI-powered precision so decisions are clearer and trials are stronger. We don’t just disrupt the pharmaceutical industry, we create lasting change.

We believe AI will define the future of medicine, and we are committed to building that future responsibly, rigorously, and in close collaboration with our partners in clinical development.


ABOUT OUR TEAM

We come from a variety of backgrounds ranging from machine learning to marketing—but regardless of where we come from, Unlearners share some common traits:

 - Unlearners are ambitious; we aren’t intimidated by big, challenging goals.

 - Unlearners are disciplined experimenters; we break down our big goals into smaller chunks and meet as often as necessary to track our velocity and iterate quickly.

 - Unlearners are gritty; we never give up, setbacks just make us try harder.

 - Unlearners are receptive to new ideas; in fact, we hate being stuck with the status quo

 - Unlearners are storytellers; sharing information with each other and with the world is super important, too important to be boring. And, last but not least,

 - Unlearners are team-oriented; we put the mission first, the company second, the team third, and individuals last.

Headquartered in San Francisco, Unlearn was founded in 2017 by a team of world-class machine learning scientists. We have raised venture capital from top tier investors such as Altimeter, Insight Partners, Radical Ventures, 8VC, DCVC, and DCVC Bio, and completed our $50 million Series C in January 2024.

If our purpose and culture resonate with you, we invite you to apply.


ABOUT THE ROLE

We are looking for an effective product manager who wants to help build new products on a computationally-focused, data-driven, AI-powered platform to solve top pain points in the pharmaceutical industry. The Product Manager will have a track record of impactful product development, a broad knowledge base of data products and cutting edge AI technologies, and a proven track record of collaboration with different types of teams including design, engineering, marketing, and business development. They will also be capable of developing a deep understanding of the problems our customers and users at biopharma companies encounter while running clinical trials. The ideal candidate must also have demonstrated experience with the techniques and methods of modern product discovery and product delivery.


RESPONSIBILITIES

 - Translate product strategy into detailed requirements, user stories, and acceptance criteria

 - Contribute to quarterly roadmap planning by shaping scope, estimating effort, and aligning cross functional partners

 - Track development and delivery progress against timelines, flag risks early, and keep stakeholders aligned

 - Run product discovery for well defined problems to validate scope and user needs

 - Run lightweight experiments, prototypes, and user tests to de-risk early concepts

 - Coordinate with design to ensure clear specs and efficient handoff

 - Partner with QA to define test plans and ensure smooth releases

 - Monitor feature usage and quality metrics to drive incremental improvements

 - Communicate status updates to leadership and cross functional teams

 - Support launch activities and operations with documentation and internal enablement


REQUIREMENTS

 - At least 3 years of product management delivering software and AI-powered products

 - Bachelor’s degree or equivalent practical experience with working knowledge of clinical drug development

 - Proven track record shipping impactful features quickly and with quality

 - Strong problem solving skills and the ability to make sound, data informed judgments under constraints to shape product direction

 - Effective cross functional collaborator across engineering, design, science and business development who can make decisions when needed and drive alignment

 - Solid technical literacy and ability to engage with engineering on architecture and implementation details

 - Ownership mindset and willingness to handle complex or ambiguous work

 - Passion for our mission


NICE TO HAVES

 - Experience in biopharma industry or in clinical development

 - Experience in fast moving or early stage environments

 - Experience building and pricing platform applications and tools


BENEFITS & PERKS

The following benefits and perks are for full time roles only.

 - Generous equity participation

 - 100% company-covered medical, dental, & vision insurance plans

 - 401k plan with matching

 - Flexible PTO plus company holidays

 - Annual company-wide break December 24 through January 1

 - Commuter benefits

 - Paid Parental Leave

Unlearn is an equal opportunity employer. 

At Unlearn, we are committed to building a diverse and inclusive workplace, because inclusion and diversity are essential to achieving our mission. If you’re excited about this role, and your past experience doesn’t align perfectly with every qualification in the job description, we encourage you to apply nevertheless. (1,372 words)
- [blog/creating-patients-digital-twins-with-neural-boltzmann-machines-for-clinical-timeseries.html](/content/blog/creating-patients-digital-twins-with-neural-boltzmann-machines-for-clinical-timeseries.html) (1 words)
- [Blog](/content/blog/introducing-unlearns-new-digital-twin-generation-architecture.html): Unlearn's new DTG architecture offers comprehensive, stochastic time-series forecasts of disease progression with significantly higher accuracy. (1,097 words)
- [Blog](/content/blog/introducing-neural-boltzmann-machines/index.html): Learn about Neural Boltzmann Machines, a new class of conditional generative model that combines feed forward deep neural networks with RBMs. (670 words)
- [trialpioneer/index.html](/content/trialpioneer/index.html) (1 words)
- [Blog](/content/blog/part-2-from-data-matching-to-trial-calibrated-digital-twins-in-oncology.html): If outcomes could be predicted for a specific population during the design phase for a trial, many of the hardest decisions in oncology development would become more tractable. (1,413 words)
- [Blog](/content/blog/part-4-when-the-oncology-head-to-head-trial-you-need-has-never-been-run.html): FOLFIRINOX and gemcitabine plus nab-paclitaxel are both established first-line treatments for advanced pancreatic cancer. Oncologists regularly choose between them, and the decision affects patients every day. (1,599 words)
- [Blog](/content/blog/part-3-how-to-stress-test-an-oncology-trial-design-during-the-design-phase.html): Before an oncology protocol is finalized, most important decisions have already been made based on untested assumptions. (1,360 words)
- [Blog](/content/blog/ad-model-update-ad-dtg-4-2-exploring-biomarker-outcomes-in-alzheimers-disease.html): This release expands the biomarker data available to our model and enables early exploration of biomarkers as potential clinical outcomes. (659 words)
- [Blog](/content/blog/decision-debt-the-cost-clinical-development-doesnt-track.html): The economics of clinical development all point the same way. More than $100 billion spent a year, 9 in 10 programs failing, $535,000 for a single Phase III amendment, most trials running late. (732 words)
- [Blog](/content/blog/projenxs-pro-101-and-the-case-for-digital-twins-in-single-arm-als.html): When ProJenX and our team presented at the ALS Drug Development Summit last year, we focused on a problem sponsors across early-stage ALS development keep running into: how to generate interpretable evidence from small, often open-label single-arm trials where no concurrent placebo arm is available. (912 words)
- [Blog](/content/blog/how-sola-biosciences-chose-to-design-sol-257-with-digital-twins-from-the-start.html): In a single-arm early-phase ALS study, the sponsor gets one read. There’s no control group to anchor against, and no way to re-run the study if the data come back hard to interpret. (755 words)
- [Blog](/content/blog/how-vectory-built-interpretability-into-pioneer-als-a-12-patient-gene-therapy-trial.html): In the United States, someone is either diagnosed with or dies from amyotrophic lateral sclerosis (ALS) every 90 minutes. The disease is universally fatal, with a median survival of two to three years after diagnosis. (688 words)
- [Blog](/content/blog/part-1-why-predicting-outcomes-has-become-the-hardest-part-of-oncology-trial-design.html): Oncology drug development has always involved making decisions with incomplete information. What has changed over the past decade is not just the scale of that uncertainty but the stakes attached to it, driven by two converging forces: patient populations are fragmenting into ever-narrower biomarker-defined subgroups, and standards of care are evolving faster than trials can read out. (911 words)
- [Blog](/content/blog/us-fda-comments-on-unlearns-procova-methodology/index.html): PROCOVA™ is a statistical methodology developed by Unlearn.AI for incorporating prognostic scores derived from trial participants’ digital twins into the design and analysis of phase 2 and 3 clinical trials. (1,118 words)
- [Blog](/content/blog/we-listened-to-sponsors-heres-what-we-built/index.html): Unlearn was founded to eliminate trial and error in medicine, and Q1 was a quarter that showed just how far that mission can reach. (1,110 words)
- [Research](/content/research/index.html): Our research teams publish on innovative AI methods and advanced disease modeling to support clinical development across therapeutic areas. (546 words)
- [Trusted by leading sponsors. Grounded in science. Proven in trials.](/content/evidence/index.html): Explore real-world examples of our AI solutions reducing trial size, increasing power, accelerating timelines, and enriching insights. (2,090 words)
- [Blog](/content/blog/index.html): Explore our blog for thought leadership about innovative AI-powered solutions for clinical trials leveraging digital twins of patients. (535 words)
- [Run quick and confident   ‍clinical trials with digital twins](/content/digital-twins/index.html): Digital twins are AI-generated forecasts of an individual trial participant’s control outcomes. By forecasting clinical outcomes at every future time point with unparalleled precision, they serve as the powering technology for a more rigorous clinical analysis. (839 words)
- [Design clinical trials with speed and rigor](/content/trialplanningandsimulations/index.html): Reach confident, evidence-backed trial design decisions earlier — before protocols are finalized. (556 words)
- [Advanced Trial Monitoring](/content/advanced-trial-monitoring/index.html): Detect patient- and site-level anomalies before the standard review cycle with AI-driven clinical data surveillance and advanced trial monitoring insights from Unlearn. (220 words)

## Resources

- [Full Page Index](/index.html): Browse all cached pages with rich metadata
- [About This Cache](/content/about.html): Methodology, technical details, and usage guidelines
- [XML Sitemap](/sitemap.xml): Machine-readable sitemap for crawler discovery
- [Robots.txt](/robots.txt): Crawler directives