AI Research Engineer, Inference

Responsibilities

We are representing a confidential quantitative finance organization seeking an AI Research Engineer focused on Inference for their advanced machine learning team in London. You will own and optimize large-scale model inference systems that directly impact live trading operations.

Your work will span multiple technical domains:

• Develop and optimize GPU kernels to maximize inference throughput and minimize latency
• Evaluate and deploy novel inference hardware including ASICs and FPGAs, both commercial and custom-built
• Design and implement efficient data streaming architectures for real-time model serving
• Collaborate closely with research scientists to co-design models optimized for production inference constraints
• Manage complex, globally distributed inference infrastructure serving multiple model types and trading strategies
• Drive technical decisions that shape the research roadmap based on inference feasibility and performance

This role offers significant technical challenges with no obvious solutions—you'll be working at the frontier of production machine learning systems where performance improvements translate directly to business impact.

What We're Looking For

Required:

• Two or more years of professional experience building deep learning systems in any domain (robotics, biology, chemistry, physics, audio, video, recommendations, etc.)
• Strong engineering skills in one or more of: CUDA/Triton/Pallas/CuTe DSL kernel development, lower-level PyTorch/JAX/XLA development, CUDA Graphs, or FPGA/ASIC implementation
• Proven ability to translate methods and techniques across different application areas

Valued but not required:

• Experience with large language model inference
• Finance or trading domain knowledge (not required—strong engineering fundamentals matter most)

The ideal candidate thrives on complex systems optimization, enjoys working at the intersection of research and production engineering, and is motivated by measurable performance impact.

How We Work With You

Get A Job.ai serves as the exclusive recruiting partner for this position. Here's our process:

• Submit your application through the Get A Job.ai platform
• Our talent team will conduct an initial screening to assess technical fit and experience
• Qualified candidates are presented directly to our client with our recommendation
• We coordinate all interview stages and provide feedback throughout
• Please do not attempt to contact the client directly—all communication flows through Get A Job.ai to ensure a smooth process

Pay

Compensation details for this role will be discussed during the screening process. Our client offers competitive base salary and performance-based bonuses commensurate with experience and the London market.

Equal Opportunity: Get A Job.ai and our clients are committed to building diverse teams. We encourage applications from candidates of all backgrounds and experiences.