Cambridge Residency Programme – Researcher in Agentic AI Systems & Infrastructure
Core
Conduct original research on the design, architecture, and optimization of agentic AI systems, focusing on memory, communication, and orchestration.
Role type
Researcher in Agentic AI Systems & Infrastructure
Builds
Multiagent inference components with system-level optimizations
Domain
Artificial Intelligence / Machine Learning Systems
Deliverable
production ML models
Required skills
ML-systems co-design, AI inference systems, independent high-impact research, modern agentic systems, orchestration patterns, largescale ML infrastructure, model post-training, reinforcement learning, supervised fine-tuning, high-performance LLM inference systems
Preferred skills
Pytorch, LLM fine-tuning on GPU clusters, vLLM, SGLang
Technologies
vLLM, SGLang, Pytorch
Responsibilities
Prototype new components for multiagent inference with system-level optimizations; Conduct original research on the design, architecture, and optimization of agentic AI systems; Evaluate proposed ideas through real-system experiments, large-scale benchmark evaluation, and empirical studies on real workloads; Explore ML & systems codesign opportunities, such as aligning model capabilities with systems constraints, hardware characteristics, and orchestration strategies
Seniority
PhD level researcher
