Inference Performance Engineer | Optimize AI Serving

adaption; Dublin; Hybrid; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Flexible work

Adaption Passport travel stipend

Lunch stipend

Well-Being benefits

Job summary

Adaption is seeking an experienced ML systems engineer who will own the cost and performance of our inference stack. You will work with the serving fleet team to optimize caching, batching, quantization, and kernel-level tuning to maximize throughput and minimize tail latency without sacrificing model quality.

You will tune routing between internal infrastructure and external providers and build profiling tools to illuminate time and memory usage.

Qualifications

• 5+ years in ML systems, inference infrastructure, or performance engineering.
• 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

Performance engineering

Python

C++

Rust

GPU performance

Tools

vLLM

SGLang

TensorRT-LLM

Job description

Adaption is seeking an experienced ML systems engineer who will own the cost and performance of our inference stack. You will work with the serving fleet team to optimize caching, batching, quantization, and kernel-level tuning to maximize throughput and minimize tail latency without sacrificing model quality.

You will tune routing between internal infrastructure and external providers and build profiling tools to illuminate time and memory usage.