Profluent Scientist II, Molecular Function at Profluent responsible for building and owning the yeast surface display platform for binder generation. Collaborates with ML and Protein Design scientists to produce model-ready binding data.
Responsibilities
Profluent is scaling the discovery engines that supply data for AI-driven protein design. We're hiring a Scientist II to build and own our yeast surface display platform for binder generation. The data you produce will train and evaluate our protein design models, and the binders that emerge will open up new directions for the company.
This role sits within the Molecular Function (MF) program, our cross-functional effort spanning ML, Biology, and Bioinformatics. You will be the scientific owner of the yeast display platform: building it hands-on, from library construction through FACS and NGS readout, then setting its direction as it scales with Profluent's design ambitions.
As the platform matures, this role will grow towards setting direction for how display and protein engineering evolve at Profluent, including how we build on the most interesting binders the platform uncovers. We are looking for a yeast display expert who is ready to take on that broader scope.
Establish and validate a yeast surface display platform for binder generation, including display vector and strain selection, library design and construction, and FACS-based selection and sorting
Design and execute yeast display campaigns across binder formats (e.g., de novo miniproteins, VHHs, scFvs, and alternative scaffolds) against a range of targets
Take workflows from concept to a robust, repeatable process: define controls, QC, and acceptance criteria, and characterize reproducibility, signal-to-noise, and the relationship between sort-bin enrichment and binding strength
Build NGS readouts into selections and deep mutational scanning workflows, converting raw sequencing counts into quantitative binding metrics that ML models can learn from
Partner with the ML scientists, and Protein Design scientists to scope campaigns (targets, library composition, readouts) and to define what "model-ready" binding data looks like
Work with Bioinformatics on metadata schemas and data ingestion so every dataset is traceable to its parent campaign
Qualification
PhD in Molecular BiologyComfortable working across disciplines
Required
PhD in Molecular Biology, Biochemistry, Protein Engineering, Biophysics, Immunology, or a closely related field, with 3+ years of relevant industry experience (level and compensation will be commensurate with experience)
Deep hands-on experience with yeast surface display, including library construction (e.g., homologous recombination, electroporation at scale), induction and expression optimization, and multi-round selection campaigns (required)
Proven track record of generating and screening libraries for binder discovery or optimization (naive, immune, synthetic, or designed)
Strong flow cytometry and FACS expertise, including gating strategy, sort design, and data interpretation
Working knowledge of NGS-based screening workflows (e.g., display library sequencing, deep mutational scanning, amplicon sequencing) and how to turn that data into a quantitative readout
Strong molecular biology skills (cloning, mutagenesis, DNA assembly)
Demonstrated ability to define and uphold assay quality standards: controls, reproducibility, and signal-to-noise
Solid understanding of protein engineering and developability considerations
Comfortable working across disciplines: can discuss binding biophysics with biologists and model-guided design with ML scientists
Experience with titration-based affinity measurement by display and sequencing (Tite-Seq–style) or analogous approaches to recovering KD from pooled data
Experience with display-based affinity maturation and binder engineering
Experience with antibody characterization (e.g., Carterra SPR, Octet BLI) and protein expression/purification
