Computational and Experimental Scientist

Job Description

Job Description

About the Role

This is a full-stack computational and experimental role at an early-stage AI-driven protein design company, sitting on a lean core team of 5 to 7 and reporting directly to the CEO. You will own the entire design-make-test-model loop, from running inference on pocket-conditioned discrete diffusion models for peptide and protein design, to generating kinetics data in the lab and feeding it back into the platform. The role matters because closing that loop faster is the core scientific and commercial advantage.

What You'll Do

• Improve and extend diffusion models and companion folding models with refinements, new attention heads, and hierarchical reasoning.

• Operate a protein design inference platform at scale and diagnose usage patterns across signups, churn, and customer segments.

• Own fluid-handling robotics and plate automation (Hamilton, Tecan, Opentrons, or equivalent) and ship reliable, production-ready protocols.

• Own BLI and SPR end-to-end: assay design, immobilization, regeneration, referencing, dilution series, kinetic fitting, QC, and failure-mode diagnosis.

• Write precise protocols for cloud labs and manage internal screening instrumentation.

• Work across receptor biology, protein structure, and scoring functions to produce outputs that working scientists can act on.

• Close the loop continuously: take sequences from the platform, run kinetics, update the model, and ship improved sequences.

What We're Looking For

• 2+ years building or operating discrete diffusion models, protein language models (such as ESM or ProtT5), or structure prediction systems in an active make-test-model loop.

• Personally written and debugged liquid-handler protocols on Hamilton, Tecan, Opentrons, or equivalent, shipped to production.

• Personally fitted BLI or SPR kinetic curves end-to-end, with the ability to diagnose failure modes such as mass transport, tip avidity, nonspecific binding, aggregation, or hook effect.

• Demonstrated ability to use sequence design tools (such as RFdiffusion or BindCraft) as inputs and outputs in a real design cycle, not as black boxes.

• Proficiency in Python or equivalent scripting for robot method coding, automation, and curve fitting.

• Background in biology, biochemistry, or a related life-science discipline sufficient to read and interpret scientific workflows.

• Operator mentality: action-oriented, comfortable working across multiple concurrent tasks, and focused on getting data rather than planning to plan.

• Background from biotech startups, accelerator programs, or prior company exits is a strong plus, as is experience in gene editing, gene therapy, or receptor trafficking.

Compensation and Benefits

Initial consulting engagement: $3,000 to $5,000 per month . Full-time conversion: base salary of $80,000 to $200,000 depending on profile, plus heavy equity and deal-contingent upside. Visa sponsorship is not available.

Location

Hybrid, based in the San Francisco Bay Area. Increased on-site presence expected once internal screening instrumentation is operational, anticipated within 3 to 6 months.