Computational Drug Discovery Intern (2026)

Octant Bio•Emeryville, CA

4d•Onsite

About The Position

We're looking for a computational drug discovery intern to join Octant this summer in a program funded by the Gates Foundation to identify small-molecule drugs targeting HPV-driven cancers. In this role, you'll work alongside our computational and experimental teams to build and iterate on machine learning models, explore molecular representations and structure-activity relationships, and help drive compound design and prioritization from data to decision.

Requirements

Currently enrolled in or recently completed a BS or MS in a quantitative field (CS, bioinformatics, applied math, data science, computational biology, or adjacent)
Proficient in Python for data analysis and scripting (pandas, numpy, scikit-learn at minimum)
Experience building or training ML models on real datasets, not just coursework exercises
At least one substantive research experience (academic lab, industry internship, or independent project) where you drove a project from question to result
Familiarity with version control (git) and working in shared codebases
Coursework or research exposure in at least one biological science area
Ability to communicate results to both computational and experimental audiences
Comfort with ambiguity and fast iteration. The project work is on a weekly cadence, which means making judgment calls with incomplete data, not waiting for perfect information

Nice To Haves

Hands-on experience with molecular representations (SMILES, fingerprints) or cheminformatics toolkits (RDKit, DeepChem)
Experience with cloud/distributed compute environments (Databricks, Spark, or similar)
Understanding of structure-activity relationships, compound libraries, or hit expansion concepts
Demonstrated ability to work across the computational-experimental boundary (e.g., designed an analysis that informed a wet-lab decision, or interpreted assay data to guide a model)
Familiarity with active learning or Bayesian optimization frameworks
Experience building or working with agentic systems, LLM tool-use pipelines, or multi-step automated workflows
Familiarity with prompt engineering and structured output parsing from language models
Experience with workflow orchestration or pipeline tools (Databricks, Airflow, or similar)
Comfort designing and consuming APIs or integrating across multiple tools/platforms programmatically
Experience with software engineering best practices beyond scripting (testing, error handling, logging, modular code design)
Familiarity with database interactions (SQL, querying structured data stores) in a production or semi-production context