About the Role
This role owns the full design-make-test-model loop at an early-stage AI-driven protein and peptide engineering company: you will run and improve pocket-conditioned discrete diffusion models for sequence design and personally execute the binding kinetics that close the loop. You will sit on a lean core team reporting directly to the CEO, making this one of the highest-leverage scientific roles at the company.
What You'll Do
Improve and extend proprietary diffusion and companion folding models with architectural refinements, new attention heads, and hierarchical reasoning.
Operate an ML 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 detailed cloud-lab protocols and manage internal screening instrumentation.
Work the full stack from receptor biology and protein structure through scoring functions to platform outputs that scientists will actually use.
Close design loops: 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 a real make-test-model cycle, not academic papers or public fine-tunes.
Personally written and debugged liquid-handler protocols on robotic platforms and shipped them to production, not supervised a core facility.
Personally fitted BLI or SPR kinetic curves end-to-end and diagnosed failure modes: mass transport, tip avidity, nonspecific binding, aggregation, hook effect, bad referencing.
Proficiency coding robot methods and analyzing kinetic data in Python or equivalent scripting.
Demonstrated ability to close a full loop: design sequences, synthesize or express, measure kinetics, update the model, iterate.
Comfortable treating protein language models and sequence design tools (such as RFdiffusion or BindCraft equivalents) as inputs and outputs, not black boxes.
Strong background in biology, biochemistry, or a closely related life-sciences field.
Operator mentality: resourceful, action-oriented, comfortable executing at odd hours to have data ready the next day.
Background in gene editing, gene therapy, or receptor trafficking is a plus.
Prior experience at biotech accelerators or early-stage biotech startups is a plus.
Compensation and Benefits
Initial consulting engagement: $3,000 to $5,000 per month. Full-time conversion: base salary $80,000 to $200,000 depending on profile, with meaningful equity and deal-contingent upside. No visa sponsorship available.
Location
Hybrid in New York, NY. On-site presence will increase once internal screening instrumentation is operational (expected within 3 to 6 months).
Originally posted on