Hands-on experience of building with LLMs/Agents is a big plus - e.g., tool and function calling, RAG, multi-step agent workflows, prompt and context engineering - through research, projects, or prior internships. Responsibilities: Engine performance, continuously improved by Agents: Build agent workflows that profile the risk engine, identify performance bottlenecks (latency, CPU, memory, cost), propose and verify optimizations, and detect performance regressions.