Sr Computational Scientist

arrow

San Francisco / $190000 - $210000 annum

INFO

Salary

SALARY:

$190000 - $210000

Location

LOCATION

San Francisco

Job Type
JOB TYPE

Permanent

About the Role


This is a high-visibility, high-impact individual contributor role sitting at the intersection of machine learning, clinical data science, and translational biology. You will lead the company's drug response prediction work - one of the most consequential and technically demanding initiatives in our portfolio.

This is not a pure research role, and it is not a pure engineering role. It requires someone who can move fluidly between rigorous quantitative analysis and the realities of working with large, messy, real-world datasets - someone who can apply state-of-the-art methods without losing sight of what actually works in practice.

The Problem We're Solving


There are thousands of drugs that work - but only for a small subset of patients, and we largely don't know why. We are building a systematic engine of understanding between drugs and biology: one that can decode the relationship between a patient's biology and their response to treatment, and translate that into insights that immediately improve care.

This is foundational, mission-critical work. The person in this role will directly shape how we approach this problem - the methods we use, the data we bring to bear, and the analytical frameworks we build. It is an opportunity to have genuine scientific and clinical impact.

What You Will Do


Drug Response Prediction

  • Lead the design and execution of computational approaches to predict drug response across patient populations
  • Develop and validate predictive models using real-world clinical data, integrating diverse data modalities
  • Identify biological and clinical signals that differentiate responders from non-responders
  • Translate modeling outputs into actionable biological and clinical insights

Data & Analysis

  • Work extensively with real-world data (RWD) - EHR, claims, clinical trial data - at scale
  • Build robust analytical pipelines that handle messy, heterogeneous, and incomplete data
  • Apply appropriate statistical frameworks to ensure rigor and reproducibility
  • Contribute to the development and evolution of internal data infrastructure and analysis tooling

Modeling & Methods

  • Apply and adapt state-of-the-art ML methods - including causal inference, survival analysis, and multi-omics integration - to biological and clinical problems
  • Balance methodological sophistication with practical performance constraints
  • Evaluate trade-offs between model complexity, interpretability, and real-world utility
  • Stay current with the literature and bring relevant advances into the team's practice

Cross-Functional Collaboration

  • Work closely with biologists, clinical scientists, and data engineers to design studies and interpret results
  • Communicate findings clearly across both technical and non-technical audiences
  • Contribute to a collaborative, intellectually rigorous team culture

What We're Looking For


Required

  • PhD in a quantitative discipline - computational biology, biostatistics, bioinformatics, computer science, physics, statistics, or a related field; open to diverse backgrounds
  • Fluent in Python - comfortable writing clean, well-structured code for data analysis and modeling
  • Real-world data experience - hands-on work with EHR, claims, or other large-scale clinical datasets
  • Ability to work with messy data at scale - experience wrangling, cleaning, and extracting signal from imperfect data
  • Strong quantitative intuition - both in modeling design and in interpreting results critically
  • Industry experience - 4+ years; 6+ preferred, ideally with both large pharma/biotech and startup exposure
  • Mission-driven - genuinely motivated by the opportunity to improve patient outcomes through better science

Strongly Preferred

  • Experience with causal inference methods (propensity scoring, instrumental variables, difference-in-differences, etc.)
  • Background in statistics, epidemiology, or biostatistics alongside ML
  • Familiarity with pharmacogenomics, multi-omics, or translational biology
  • Experience contributing to or extending data infrastructure and analysis frameworks
  • Track record of working across interdisciplinary teams (biology, chemistry, clinical)
  • Startup experience - comfort with ambiguity, ownership, and moving quickly

Background & Experience Profile


We are open to a wide range of PhD backgrounds - what matters most is strong quantitative and analytical foundations, genuine intellectual curiosity, and the ability to work rigorously with complex biological and clinical data. Prior biology experience is not required, but candidates with some exposure to biological or clinical domains will be viewed favorably.

The ideal candidate has spent time in both large pharma/biotech (where they developed rigor and depth) and a startup environment (where they developed speed and ownership). If you haven't done both, a trajectory that moves toward increasing independence and scope is what we're looking for.


CONTACT

Tim Lucas

Manager

SIMILAR
JOB RESULTS

4k-Harnham_DA copy
CAN’T FIND THE RIGHT OPPORTUNITY?

STILL
LOOKING?

If you can’t see what you’re looking for right now, send us your CV anyway – we’re always getting fresh new roles through the door.