Develop agentic AI systems using rigorous evaluation science; implement reasoning, planning, memory, and generalization capabilities; build benchmarking methodologies to assess agent performance. Support cross-functional stakeholders in Commercial, Manufacturing, Clinical Development, and Research.

• Research reasoning/planning/memory/generalization architectures for AI and multi‑agent systems; build cognition frameworks (abstraction, goal decomposition, adaptive planning).
• Design and run benchmarking/evaluation experiments; create evaluation datasets, test harnesses, and measurement frameworks; apply experimental design and statistical analysis.
• Engineer and deploy agentic solutions: multi‑agent systems (e.g., Strands, LangGraph, DSPy), RAG applications, knowledge graphs, conversational AI, and autonomous workflows.
• Rapid prototype and translate research into production‑ready capabilities; document researc...