Research Engineer (Inference & Serving)

This role focuses on building and operating the inference stack for a multimodal agentic model in production. You'll work at the intersection of research and production, optimizing latency, throughput, and cost for computer-use agent workloads, while co-designing with the model team.

• Build and operate the inference stack serving multimodal agentic models in production
• Improve latency, throughput, and cost across the serving stack
• Research and implement inference techniques tailored to agent workloads
• Co-design with the models team on training-time decisions that affect inference behaviour
• Evaluate inference frameworks and hardware platforms and feed findings back into roadmap decisions
• Stay current with advances in inference, model serving, and accelerator technology

• Strong software engineering fundamentals and a solid production track record
• Proficient in Python and at least one systems language (Rust, C++, or Go)
• Hands-on experience with PyTorch or JAX in an industry setting
• Experience with inference frameworks: vLLM, SGLang, TensorRT-LLM
• Solid distributed systems fundamentals and experience operating production ML infrastructure
• Working knowledge of modern ML including transformers and multimodal architectures