Protein Design Scientist, Agentic Workflows

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. We're looking for a Protein Design Scientist to own the development and deployment of agentic workflows for protein design. In this role, you will build systems that orchestrate protein language models, structure predictors, fitness scoring tools, and experimental feedback into automated or semi-automated design pipelines - closing the loop between computation and the wet lab. This is a hands-on, high-ownership role. You'll work across the full stack of a design workflow: selecting and integrating models, defining agent logic and iteration strategies, building robust infrastructure for deployment, and collaborating closely with ML scientists, protein design scientists, and biologists to ensure your systems produce experimentally actionable results. As an early employee, you will shape how Profluent approaches workflow automation and help define best practices for agentic systems in protein engineering. Responsibilities Design, build, and deploy end-to-end agentic workflows that take protein function specifications and produce ranked candidate sequences for experimental validation Integrate protein language models, structure prediction tools, and scoring functions into multi-step pipelines with iteration, feedback loops, and human-in-the-loop checkpoints Own the full lifecycle of workflow systems: architecture, implementation, testing, deployment, monitoring, and iteration based on experimental outcomes Collaborate with ML scientists to evaluate and integrate new models into workflows, and with protein design scientists and biologists to translate scientific goals into computational specifications and ensure workflows align with experimental realities Develop tooling for experiment tracking, logging, reproducibility, and versioning of design campaigns Evaluate and benchmark workflow performance against experimental results, using outcomes to improve agent strategies and model selection Partner with ML scientists to identify where existing models fall short in agentic contexts and inform priorities for model development, fine-tuning, and evaluation Qualifications PhD (or equivalent industry experience) in Computational Biology, Bioinformatics, Computer Science, Machine Learning, Biochemistry, or a related field Minimum of 3+ years of experience as a protein design scientist Strong software engineering skills: you write clean, modular, production-quality code (Python required; experience with workflow orchestration frameworks is a plus) Hands-on experience with protein language models (e.g., ESM, ProGen, ProtTrans) for sequence generation, scoring, or representation Demonstrated understanding of protein engineering principles: structure-function relationships, fitness landscapes, and how computational predictions connect to wet-lab validation Experience building multi-component systems that chain model inference with data processing, filtering, and decision logic Preferences (but not required) Experience with agentic AI systems, LLM tool-use patterns, or multi-step reasoning pipelines Familiarity with structure prediction tools (AlphaFold, RoseTTAFold, ESMFold) and inverse folding methods (ProteinMPNN, LigandMPNN) Track record of computational designs that were experimentally validated Experience with cloud compute platforms (GCP, AWS, Azure) and containerized deployment (Docker, Kubernetes) Publications in protein design, protein engineering, or ML for biology at major conferences or journals Familiarity with directed evolution, rational design, or de novo protein design strategies What We Offer High-growth opportunity w