Research Scientist

Latent Labs•San Francisco, CA

About The Position

Latent Labs is hiring hands-on Scientists and a Senior Scientist to work at the interface of generative AI and biology. The team’s models design novel proteins, while its experimental scientists develop and run assays to characterize protein properties and functions, identify strengths and failure modes, and guide subsequent model development. The role involves developing and executing high-throughput assays, drawing on molecular biology, mammalian cell culture, and experimental design. The scientist will select methods according to the scientific question, bring depth in at least one relevant technical area, and collaborate with experimental scientists, machine-learning researchers, automation colleagues, and technical expert consultants to establish reliable workflows and generate high-quality, interpretable data. The Senior Scientist role additionally calls for mentoring experience, more years of industry experience, and ownership of complex CRO projects, including understanding statements of work, negotiating contracts, and troubleshooting.

Requirements

PhD in molecular biology, cell biology, biochemistry, or a related field.
At least 1–3 years of relevant industry research experience for Scientist; more than 3 years for Senior Scientist.
Ability to take an assay from initial feasibility testing through optimization and reproducible execution.
Experience developing or running high-throughput experiments, ideally using plate-based assays and laboratory automation.
Understanding of how experimental design, controls, and sample handling affect data quality.
Experience in molecular biology and mammalian cell culture, alongside relevant methods such as molecular cloning, cell-based functional assays, flow cytometry/FACS, ELISA, or next-generation sequencing. Expertise in every listed technique is not required.
Proficiency in Python and Jupyter notebooks for experimental-data processing, analysis, and visualization, with the ability to produce clear, reproducible analyses.
Accurate experimental recordkeeping and experience with Benchling, a LIMS, or comparable tools for tracking samples and associated data.
Depth in at least one relevant technical area, with the ability and interest to learn adjacent methods: gene editing or protein–DNA interaction characterization; membrane-protein characterization; or protein biochemistry and biologics characterization.

Nice To Haves

Experience in an early-stage biotech, including establishing assays, workflows, or laboratory processes.
Experience transferring consultant-developed or externally developed assays into an internal lab.
Experience improving automated screening workflows or sample and data management systems.
Familiarity with Git and GitHub for version control and collaborative analysis.
Experience working with computational scientists or evaluating computationally designed proteins.
For the Senior Scientist role: experience mentoring others in professional and technical contexts, additional industry experience, and managing complex CRO projects with full ownership, including understanding SOWs, negotiating contracts, and troubleshooting.

Responsibilities

Independently design, execute, optimize, and troubleshoot cell-based and biochemical assays to evaluate model-generated proteins, emphasizing high-throughput plate-based workflows.
Work with technical expert consultants to select and implement new assays, interpret unfamiliar data, and translate specialist knowledge into reproducible internal workflows.
Collaborate with the automation team to improve screening throughput, reproducibility, and efficiency, and contribute to development of the screening platform.
Use Python to process experimental data, assess assay quality, and communicate findings and limitations; establish controls and quality-control criteria.
Document methods, samples, experimental conditions, and analysis results using Benchling, a LIMS, or similar tools.
Work with machine-learning colleagues to provide well-documented data and biological context and translate results into actionable insights for subsequent design cycles.