Research Engineer, Model Inference & Serving

🔒 Confidential Employer
Posted 18 May 2026
LOCATION
London
TYPE
Full-time
LEVEL
Mid-Senior level
CATEGORY
Software Engineering
This employer holds a UK Home Office sponsor license — sponsorship for this specific role is at the employer’s discretion

SKILLS

Python PyTorch Kubernetes Distributed Systems Inference Frameworks (vLLM) GPU Programming (CUDA) Multimodal Models Communication Skills

FULL DESCRIPTION

Research Engineer, Model Inference & Serving - London

[Employer hidden — sign up to reveal] is hiring a Research Engineer for Model Inference & Serving to build and operate inference systems for multimodal agentic AI models. The role involves improving latency, throughput, and cost, researching inference techniques, and collaborating with cross-functional teams. Requires strong software engineering, Python, deep learning frameworks, distributed systems, and experience with inference frameworks like vLLM. Hybrid work in London or Paris.

About [Employer hidden — sign up to reveal]

[Employer hidden — sign up to reveal] exists to push the boundaries of superintelligence with agentic AI. By automating complex, multi-step tasks typically performed by humans, AI agents will help unlock full human potential. [Employer hidden — sign up to reveal] is hiring the world's best AI talent, seeking those who are dedicated as much to building safely and responsibly as to advancing disruptive agentic capabilities. We promote a mindset of openness, learning, and collaboration, where everyone has something to contribute.

About the Team

The Inference team builds and operates the systems that serve [Employer hidden — sign up to reveal]'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., disaggregated inference, intelligent routing). Agentic inference brings constraints around context length, multimodality, and tool calls, which we address by co-designing with the Models team on training-time choices and with the agent teams on how models are deployed. We operate at the intersection of research and production, translating cutting-edge inference techniques into the systems that power [Employer hidden — sign up to reveal]'s next generation of agents. We are looking for strong engineers excited about inference to join the team and help shape the systems behind superintelligent AI.

Key Responsibilities

  • Build and operate the inference stack that serves [Employer hidden — sign up to reveal]'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
  • Evaluate inference, serving, and hardware platforms, and communicate findings to stakeholders
  • Stay current with advancements in inference, model serving, and accelerator technology

Requirements

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
  • Experience working in a modern cloud environment and with production ML infrastructure (Kubernetes, etc.)
  • Working knowledge of modern ML, including transformers and multimodal architectures

Research Skills:

  • Research engagement: an advanced degree with research output, or publications at top-tier AI or systems venues (e.g., NeurIPS, ICML, MLSys, OSDI), research internships, or substantive open-source contributions

Soft Skills:

  • Excellent communication and presentation skills
  • Strong collaboration and teamwork skills
  • Passion for inference and AI

Preferred Qualifications:

  • Startup experience
  • Hands-on experience with inference frameworks (vLLM, SGLang, TensorRT-LLM)
  • Writing or modifying GPU kernels (CUDA, Triton, etc.)
  • Edge or on-device inference experience (llama.cpp, MLX, ONNX Runtime, etc.)
  • Experience with quantization, speculative decoding, disaggregated inference or KV-cache compression
  • Experience with multimodal models and/or agentic systems

Location

Paris or London. This role is hybrid, and you are expected to be in the office 3 days a week on average. Please expect some travel between offices on a reasonable cadence (e.g., every 4-6 weeks).

What We Offer

  • Join the exciting journey of shaping the future of AI
  • Collaborate with a fun, dynamic and multicultural team, working alongside world-class AI talent in a highly collaborative environment
  • Enjoy a competitive salary
  • Unlock opportunities for professional growth, continuous learning, and career development

Powered by Ashby | Privacy Policy | Security | Vulnerability Disclosure

Sign up free — access 45,000+ UK sponsor-licensed jobs