Scientist II, ML - Guided Protein Design Evaluation

Profluent is an AI-first protein design company. Founded in 2022, we develop deep generative models to design and validate novel, functional proteins to revolutionize biomedicine. Based in Emeryville, CA, we are backed by leading investors including Altimeter Capital, Bezos Expeditions, Spark Capital, Insight Partners, Air Street Capital, AIX Ventures, and Convergent Ventures, and have raised over $150M to date.

The Role We are expanding the ML Design Evaluation (MDE) program; the cross-functional program that runs dedicated, structured design campaigns to generate high-quality experimental data for Profluent’s protein design models. MDE sits at the intersection of ML, Biology, and Bioinformatics, and its output directly translates into improved models and accelerated protein design campaigns. We are looking for a scientist with deep expertise in therapeutic antibody development, protein engineering, and ML-guided protein design to partner with the MDE Lead on the scientific substance of the program.

You will own the translation between what our ML team needs to learn from each campaign and what the experimental system (internal assays and CRO-run workflows) can deliver. You will help scope targets and assays, partner with ML scientists to define what “model-ready” data looks like for each campaign, set and enforce assay readiness and QC expectations, and close the Design→ Build→ Test→ Learn loop by tracking how each dataset impacts model performance. This is a hands-on technical role, not a pure program role.

You’ll collaborate with ML and Protein Design scientists to develop experimental designs, review assay protocols, troubleshoot data quality issues with internal teams and CROs, and work closely with ML scientists to understand how data is used in model training.

Responsibilities

Partner with ML and Protein Design leads to scope MDE campaigns; including target selection, choice of assays, and what readouts are needed to improve the next generation of models Define assay readiness levels, controls, and QC acceptance criteria for each campaign, and enforce them across internal execution and external CROs Review incoming data (biochemical, biophysical, NGS-based screens) for scientific soundness before it is accepted into the data warehouse and used for model training Work with Bioinformatics on metadata schemas and data ingestion so that every dataset is consistent, queryable, and traceable back to its parent project.

Qualifications

PhD in Molecular Biology, Biochemistry, Protein Engineering, Biophysics, Immunology, or a closely related field; or MS with equivalent industry experience 5+ years of hands-on experience with protein engineering and functional characterization, including biochemical activity, binding, stability, and/or expression assays Direct experience with therapeutic antibody discovery and engineering (e.g., affinity maturation, developability optimization, humanization, format engineering) and the assays that support it (binding kinetics, epitope characterization, biophysical and developability panels) Strong working knowledge of NGS-based screening workflows (e.g., deep mutational scanning, amplicon sequencing, high-throughput activity screens, antibody display library sequencing) and what makes that data usable for modeling Demonstrated ability to define assay quality standards (signal/noise, reproducibility, plate-level controls) and hold experimental workflows to them Fluent working across scientific disciplines; can talk protein chemistry and ant