SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 150,000 - 185,000 / annual
BioAge Labs is seeking a Translational AI Scientist/Engineer to design and deploy agentic AI systems that support scientific reasoning and evidence synthesis for drug discovery and translational science. The role bridges AI engineering and translational biology, focusing on building production-grade systems that take a drug target and produce decision-grade, evidence-backed recommendations—from mechanism hypotheses to validation design—with every claim grounded in retrievable evidence.
Key Responsibilities:
- Design and deploy agentic AI systems for hypothesis generation, mechanism discovery, and evidence synthesis in translational science contexts
- Build systems that recommend experimental approaches (in vivo, ex vivo, in vitro models, indications, endpoints, intervention modalities) grounded in published precedent
- Develop tool-using workflows that retrieve and integrate structured and unstructured evidence (knockout phenotypes, endpoint precedent, effect sizes, reagent quality, primary literature) with full provenance tracking
- Build cross-species translation layers to determine whether human-derived signals reproduce in model systems and identify readouts linking experimental results back to human cohort data
- Assess translatability by developing evidence that human-derived signals will reproduce in vivo, calibrated against targets with known preclinical and clinical outcomes
- Design evaluation frameworks for these systems, including reference sets of targets with known outcomes, metrics for citation quality and coverage, and calibration of translatability calls
- Encode domain rules on the meaning and reliability of external sources so that absent, weak, and contradicting evidence are handled distinctly
- Partner with target biology and experimental teams to ensure recommended designs are usable and incorporate study outcomes back into the system
- Own systems end-to-end (architecture, implementation, testing, deployment, monitoring) as maintainable software that scientists rely on daily
The ideal candidate combines hands-on expertise in building generative and agentic AI systems with a strong foundation in target discovery, drug discovery, and translational science. You should prefer building production AI systems over running one-off analyses and have enough hands-on biology to judge whether a recommendation is scientifically sound.
Requirements:
- PhD with 2+ years of relevant experience, OR Master's degree with 5+ years, OR Bachelor's degree with 7+ years in computer science, computational biology, biology, translational science, or related field
- Hands-on experience building and deploying LLM-based agentic systems in production or production-like settings (tool use, retrieval over structured/unstructured sources, multi-agent orchestration, structured outputs, provenance tracking, cost/latency management)
- Experience designing and running evaluation for AI systems (reference sets, automated metrics, regression testing) with strong understanding of interpretability and scientific reliability in decision-critical environments
- Strong software engineering fundamentals: Python, testing, version control, API design, data modeling, reproducible and auditable workflows (orchestration, documentation, CI)
- Experience integrating multi-modal biological data (omics, phenotype, perturbation, text, literature) using AI-enabled or model-based approaches
- Experience with research AI infrastructure: relational and graph databases, cloud environments and containers, pipeline orchestration, programmatic access to large public biological databases
- Hands-on or wet-lab research experience in one or more of: in vivo pharmacology, disease models, target validation, disease biology, functional genomics, chemical biology, or translational science
- Working knowledge of resources holding target and precedent evidence (model organism phenotype databases, chemical probe resources, drug/clinical trial databases, pathway resources)
- Familiarity with evidence linking preclinical results to clinical outcomes, including genetic support and animal-to-human translation literature
- Scientific rigor about evidence: distinguish absence of evidence from evidence against, report coverage alongside conclusions, prefer stating gaps to filling them plausibly
- Ability to work effectively across scientific and engineering functions with strong written and oral communication, self-motivation, and independence
Preferred: Background in aging biology or geroscience; experience with proteomics, cross-species biomarker translation, or biomedical ontologies; familiarity with CRISPR, perturbation resources, or pooled/arrayed screening.
