Inference Systems Performance Engineer for AI Serving

adaption; Greater London; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Flexible work

Lunch stipend

Well-Being benefits

Job summary

Adaption is seeking a senior ML systems engineer to own the cost and performance of our inference stack in a rapidly evolving environment. You will shape throughput, latency, and reliability by tuning caching, batching, and kernels while collaborating with the serving fleet engineers.

You will work with engines like vLLM, SGLang, and TensorRT-LLM, and build tools to measure where compute is spent. A strong background in Python and systems languages is essential, with a track record of real-world

Qualifications

• 5+ years in ML systems, inference infrastructure, or performance engineering with measurable improvements in cost or latency.
• Deep understanding of model serving, including prefill and decode, memory bandwidth, batching, and concurrency.
• Production experience with serving engines such as vLLM, SGLang, or TensorRT-LLM.
• Strong Python skills and proficiency in C++, Rust, or another systems language.
• Experience with GPU performance including CUDA, NCCL, mixed precision, memory layout, kernels, or quantization.

Responsibilities

• Improve throughput, cost, and tail latency through KV-cache management, continuous batching, speculative decoding, and quantization.
• Optimize long-context prefill and decode workloads based on real production traffic.
• Tune routing between our infrastructure and external providers based on cost, capacity, and performance.
• Work within serving engines such as vLLM, SGLang, and TensorRT-LLM, going below the framework when needed.
• Build profiling and measurement systems that show where time, memory, and compute are being spent.

Skills

ML systems

Inference infrastructure

Performance engineering

Python

C++

Rust

GPU performance

Tools

vLLM

SGLang

TensorRT-LLM

CUDA

NCCL

Job description

Adaption is seeking a senior ML systems engineer to own the cost and performance of our inference stack in a rapidly evolving environment. You will shape throughput, latency, and reliability by tuning caching, batching, and kernels while collaborating with the serving fleet engineers.

You will work with engines like vLLM, SGLang, and TensorRT-LLM, and build tools to measure where compute is spent. A strong background in Python and systems languages is essential, with a track record of real-world