It runs applied research (ML and agentic/LLM systems, planning, simulation and evaluation), rapid prototyping and production engineering (APIs, CI/CD, observability, data platforms and cost/latency optimisation), and rigorous evaluation and safety work (benchmarks, red-teaming, monitoring, governance and compliance). * Design and implement scalable, production-grade Python services that leverage LLMs and Agentic architectures. * Proven experience designing and deploying Agentic or LLM-powered systems in production, ideally within enterprise or regulated environments. * Experience developing production APIs and backend services that integrate with enterprise systems and data sources.
plus