Computational and Experimental Scientist

About the Role

This is a full-stack scientist role at an early-stage AI-driven protein and peptide design company, sitting directly on a lean core team of 5 to 7 and reporting to the CEO. You will own the entire design-make-test-model loop, from sequences out of the inference platform to kinetics data back in, closing that loop end-to-end rather than handing off between functions.

What You'll Do

Improve and extend pocket-conditioned discrete diffusion models and companion folding models, including refinements, new attention heads, and hierarchical reasoning. Operate the AI inference stack at scale and diagnose usage patterns across signups, churn, and customer segments. Own fluid-handling robotics and plate automation (Hamilton, Tecan, Opentrons, or equivalent), writing and shipping reliable protocols.

Own BLI and SPR end-to-end: assay design, immobilization, regeneration, referencing, dilution series, kinetic fitting, QC, and failure-mode diagnosis. Write protocols for cloud labs and manage internal screening instrumentation. Work the full stack across receptor biology, structure, scoring, and platform output.

Take sequences from the platform, run kinetics, update models, 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 design-make-test cycle, not just academic fine-tuning. Personally written and debugged liquid-handler protocols on robotic platforms and shipped them to production. Personally fitted BLI or SPR kinetic curves end-to-end and diagnosed failure modes such as mass transport, tip avidity, nonspecific binding, aggregation, or hook effect.

Fluent with sequence design tools (such as RFdiffusion or BindCraft) as inputs and outputs, not as black boxes. Able to explain why a predicted ddG failed on a sensor and trace the root cause. Proficient in Python or equivalent scripting for automation and kinetic curve fitting.

Strong background in biology, biochemistry, or life sciences, with receptor biology and protein structure literacy. Operator mentality: resourceful, action-oriented, and comfortable executing under pressure at an early-stage company. Background in gene editing, gene therapy, or receptor trafficking is a plus.

Prior experience at biotech accelerators or as an operator at a biotech startup or exit is a plus. 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, with meaningful equity and deal-contingent upside.

No visa sponsorship is available. Location Hybrid, with increased on-site presence expected once internal screening infrastructure is established (roughly 3 to 6 months out). Primary location is San Francisco, California, US.

ABOUT THE ROLE

This is a full-stack scientist role at an early-stage AI-driven protein and peptide design company, sitting directly on a lean core team of 5 to 7 and reporting to the CEO. You will own the entire design-make-test-model loop, from sequences out of the inference platform to kinetics data back in, closing that loop end-to-end rather than handing off between functions.

WHAT YOU'LL DO

• Improve and extend pocket-conditioned discrete diffusion models and companion folding models, including refinements, new attention heads, and hierarchical reasoning.
• Operate the AI inference stack at scale and diagnose usage patterns across signups, churn, and customer segments.
• Own fluid-handling robotics and plate automation (Hamilton, Tecan, Opentrons, or equivalent), writing and shipping reliable protocols.
• Own BLI and SPR end-to-end: assay design, immobilization, regeneration, referencing, dilution series, kinetic fitting, QC, and failure-mode diagnosis.
• Write protocols for cloud labs and manage internal screening instrumentation.
• Work the full stack across receptor biology, structure, scoring, and platform output.
• Take sequences from the platform, run kinetics, update models, 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 design-make-test cycle, not just academic fine-tuning.

• Personally written and debugged liquid-handler protocols on robotic platforms and shipped them to production.
• Personally fitted BLI or SPR kinetic curves end-to-end and diagnosed failure modes such as mass transport, tip avidity, nonspecific binding, aggregation, or hook effect.
• Fluent with sequence design tools (such as RFdiffusion or BindCraft) as inputs and outputs, not as black boxes.
• Able to explain why a predicted ddG failed on a sensor and trace the root cause.
• Proficient in Python or equivalent scripting for automation and kinetic curve fitting.
• Strong background in biology, biochemistry, or life sciences, with receptor biology and protein structure literacy.
• Operator mentality: resourceful, action-oriented, and comfortable executing under pressure at an early-stage company.
• Background in gene editing, gene therapy, or receptor trafficking is a plus.
• Prior experience at biotech accelerators or as an operator at a biotech startup or exit is a plus.

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, with meaningful equity and deal-contingent upside. No visa sponsorship is available. LOCATION Hybrid, with increased on-site presence expected once internal screening infrastructure is established (roughly 3 to 6 months out). Primary location is San Francisco, California, US.