AI Biologist - Gene Therapy Discovery

LatchBio•San Francisco, CA
•$140,000 - $180,000•Remote

About The Position

Latch builds scientific benchmarks for AI agents across biology and works with frontier labs and pharmaceutical companies to assess whether agents can handle real biological workflows. The AI Biologist will serve as the scientific authority on ground truth for the Gene Therapy Discovery team, evaluating whether AI agents can reason like expert gene therapy scientists and building tasks and datasets for benchmarks across AAV, lentiviral, and non-viral delivery, from target tissue selection to candidate nomination. The role involves writing defensible gold-standard answers, designing scenarios across the gene therapy discovery process, curating datasets from real programs, and building Python analysis pipelines where useful. The successful candidate will identify artifacts and limitations in experimental evidence, adjudicate conflicting results, weigh scientific and development tradeoffs, and recommend experiments that resolve uncertainty. They will also evaluate agents' reasoning step by step, identify scientifically unsound conclusions, explain what evidence would change a judgment, and score confidence while rewarding appropriate uncertainty. In the United States, the position is full-time W-2. Outside the United States, it is contractor work. The role may be remote or onsite at Latch's Mission Bay office in San Francisco; onsite work is preferred.

Requirements

  • PhD in molecular biology, virology, genetics, bioengineering, or a related field; an MS with equivalent hands-on program experience also qualifies.
  • 2 to 6 years of hands-on gene therapy experience at a biotech or pharmaceutical company.
  • Personal analysis work within the last two years.
  • Personally generated or analyzed data that determined which vector, capsid, promoter, or payload advanced, and ability to identify the threshold and decision.
  • Direct experience in at least one of the following: capsid or vector engineering and library screening; promoter and regulatory element design; transduction and expression assays; tropism or biodistribution analysis; or vector immunogenicity.
  • Deep expertise in one listed area and fluency across the others.
  • Strong experimental design, quantitative analysis, and statistics.
  • Daily use of Claude, Cursor, or a similar AI tool, with the judgment to spot technically correct but scientifically unsound reasoning and confidence to overrule it.

Nice To Haves

  • Python or R experience for personal analyses.
  • Gene-editing delivery or non-viral delivery experience, including LNP, nanoparticle, or electroporation.

Responsibilities

  • Write gold-standard answers and supporting rationales that an experienced vector scientist would defend.
  • Design benchmark scenarios across capsid or vector selection, promoter and regulatory element choice, payload design within packaging limits, transduction and expression, tropism, and early immunogenicity triage.
  • Curate datasets from real gene therapy programs, including library NGS, vector titers, infectious unit assays, transduction and expression results, tropism, biodistribution, and innate immune readouts.
  • Build analysis pipelines in Python where useful, with tolerances that hold across replicates and analytical methods.
  • Identify experimental artifacts and assess what data do and do not support.
  • Adjudicate conflicting evidence and identify experiments that would resolve the conflict.
  • Evaluate tradeoffs among tropism, expression, payload size, promoter properties, immunogenicity, and manufacturability.
  • Interrogate AI agents' reasoning, identify where their conclusions are scientifically unsound, and explain what evidence would change the assessment.
  • Score agent confidence and reward explicit uncertainty when data are ambiguous.

Benefits

  • In the US, health, dental, and vision coverage is 100% covered for the employee and 50% covered for dependents.
  • 401(k) with no match.
  • 15 days of PTO to start, with more as the employee is promoted.
  • First four weeks are paid at full OTE during ramp.
  • Full OTE is paid when quota cannot fairly apply, such as at the start of a new project, during platform downtime, or when assigned to a special project.
  • Outside the US, 60% of monthly OTE is paid up front as an advance against later earnings.
  • Company outings most months and team off-sites.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service