Research Engineer, Model Inference & Serving - London

Job summary

Responsibilities

About the Team: The Inference team builds and operates the systems that serve H's foundational models in production. We focus on multimodal inference and serving for Computer Use Agents, optimizing across both the inference engine layer (e.g., vLLM, SGLang) and the model serving layer (e.g.…

• Build and operate the inference stack that serves H's multimodal agentic models
• Improve latency, throughput, and cost of model serving across the stack
• Research and implement inference techniques tailored to agent workloads
• Co-design with the Models team on training-time decisions that affect inference
• Collaborate with cross-functional teams to integrate inference into agentic AI products

What they're looking for

• Technical skills:
• Strong software engineering track record
• Proficient in Python and at least one systems language (Rust, C++, or Go)
• Hands-on experience with deep learning frameworks (PyTorch, JAX), preferably in an industry setting
• Solid distributed systems fundamentals

Tech stack

• vLLM
• Python
• Rust
• C++
• Go
• PyTorch
• JAX
• Kubernetes