Responsibilities

• Drive AI agent development from research and experimentation through production deployment.
• Enhance agent capabilities such as planning, reasoning, tool usage, memory, and multi-agent workflows based on measurable results.
• Build evaluation frameworks to assess agent performance and validate improvements.
• Identify agent limitations and develop practical solutions to improve reliability and performance.
• Contribute to technical direction, code reviews, mentoring, and engineering standards.
• Apply recent AI research to production while balancing reliability, latency, and cost.

Requirements

• PhD in Computer Science, AI, ML, or a quantitative field related to autonomous systems/NLP.
• Senior experience developing production-grade AI agents with planning, tool use, and multi-step reasoning; ~6+ years in software/ML or equivalent depth.
• Proven ability to turn research concepts into production solutions with measurable impact.
• Strong knowledge of agent architecture, orchestration, context/state management, and tool integration.
• Strong experience designing evaluations for non-deterministic AI systems and making data-driven decisions.
• Strong Python, system design, and ability to understand ML/agent research papers.
• Able to provide technical guidance, mentor engineers, and influence team direction.

Preferred

• Experience with scientific/research environments, especially drug discovery or similar experimental domains.
• Previous mentoring or technical leadership experience.
• Knowledge of RAG, memory systems, multi-agent architectures, or bio/chemistry.