Scientist II, ML - Guided Protein Design Evaluation

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.

• →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.
• →Serve as the scientific point of contact for CRO technical scoping; evaluate whether a vendor’s platform, assay conditions, and controls are fit for purpose for ML-guided optimization
• →Contribute to campaign charters, benchmarking assay design, and post-campaign readouts; help turn individual experiments into a growing institutional dataset
• →Represent the MDE program in cross-functional technical forums and help raise the data-quality bar across the organization

• 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 antibody biology with biologists and model-guided design approaches with ML scientists without losing either audience

• Prior experience closing Design–Build–Test–Learn loops in an industrial protein design, antibody engineering, or directed evolution setting
• Experience with display-based antibody discovery platforms (phage, yeast, mammalian) and/or single-cell B-cell screening workflows
• Experience scoping and overseeing externally run assays at CROs, including technical evaluation of vendor platforms
• Comfortable with Python/pandas and SQL at the level needed to inspect, QC, and reason about experimental datasets independently
• Familiarity with LIMS and project-management systems and experience defining data & metadata schemas for experimental data
• Exposure to kinases, nucleases, recombinases, or gene editing enzymes is a plus
• Track record of publishing, presenting, or shipping work at the intersection of protein engineering and machine learning

Legal authorization to work in the United States is required. In compliance with federal law, all persons hired must verify their identity and work eligibility and complete the required employment verification form upon hire.