Computational Biology AI Tools Engineer

We are looking for a hands-on engineer to help integrate computational biology models, bioinformatics tools, and scientific workflows into an AI platform. This person will work on connecting biological foundation models, sequence analysis tools, research APIs, structured scientific datasets, and AI-accessible workflows so they can be used reliably by agents and researchers. The role is focused on in-silico systems: model integration, tool design, evaluation, data handling, workflow automation, and safe deployment of computational biology capabilities. The ideal candidate is comfortable working at the intersection of software engineering, AI systems, and biology. They should be able to turn complex scientific tools into well-defined agent tools, design safe inputs and outputs, test realistic workflows, evaluate model behavior, and help ensure that biological AI capabilities are implemented responsibly. Skills •⁠ ⁠Strong Python experience. •⁠ ⁠Experience with computational biology, bioinformatics, genomics, protein analysis, or biological sequence data. •⁠ ⁠Familiarity with biological foundation models, genomic language models, protein models, or related AI-for-biology systems. •⁠ ⁠Experience integrating open-source models, research codebases, APIs, SDKs, or scientific tools into production-like systems. •⁠ ⁠Ability to work with sequence formats, biological datasets, metadata, annotations, embeddings, and model outputs. •⁠ ⁠Experience with tools or libraries such as Biopython, PyTorch, Hugging Face, NVIDIA BioNeMo, AlphaFold-related tooling, protein language models, or genomic model frameworks. •⁠ ⁠Ability to design AI-accessible tools with clear inputs, outputs, validation rules, and safe operating boundaries. •⁠ ⁠Experience with agent-tool integration, function calling, MCP, workflow automation, or AI orchestration systems. •⁠ ⁠Understanding of model evaluation, benchmarking, reproducibility, and scientific validation. •⁠ ⁠Ability to test workflows using controlled datasets, sandbox environments, and documented expected outputs. •⁠ ⁠Strong debugging skills for model failures, dependency issues, malformed inputs, memory constraints, long-running jobs, and inconsistent scientific outputs. •⁠ ⁠Familiarity with REST APIs, JSON, structured schemas, asynchronous jobs, queues, and long-running compute workflows. •⁠ ⁠Backend API experience, preferably with FastAPI or similar frameworks. •⁠ ⁠Experience with PostgreSQL, Redis, object storage, or scientific data pipelines. •⁠ ⁠Basic Docker, cloud deployment, GPU environments, or containerized research tooling experience. •⁠ ⁠Understanding of responsible AI, data governance, access control, audit logs, and appropriate safeguards for biology-related tools. •⁠ ⁠Ability to read research papers and translate them into practical engineering tasks. Nice to Have •⁠ ⁠Experience with Evo 2, genomic foundation models, protein design models, molecular property prediction, or biological sequence generation systems. •⁠ ⁠Experience building evaluation harnesses for scientific or research models. •⁠ ⁠Experience with workflow tools such as n8n, Airflow, Prefect, or similar systems. •⁠ ⁠Experience deploying GPU-backed inference services. •⁠ ⁠Familiarity with biosecurity-aware development, dual-use risk review, or responsible research practices. •⁠ ⁠Experience building internal developer tools, SDKs, or agent-accessible scientific APIs. Important Note This is a computational and software engineering role. The work is focused on in-silico model integration, research tooling, workflow automation, evaluation, and responsible AI system design. It does not involve wet-lab work, clinical advice, human-subject research, or unsupervised biological experimentation.