Inference Performance Engineer: Latency & Cost Optimizer

adaption; Singapore; Hybrid; SGD 120,000 - 160,000; Full time

Benefits offered by this job

Flexible work

Adaption Passport

Lunch Stipend

Well-Being

Job summary

adaption is seeking an experienced ML systems engineer to own the cost and performance of our inference stack, ensuring efficient model serving as workloads and hardware evolve. You will collaborate with the serving fleet to optimize caching, batching, quantization, decoding, and kernel-level tuning for higher throughput and lower latency without sacrificing reliability or model quality.

You will drive improvements in long-context prefill and decode workloads, optimize routing to external

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++

Tools

vLLM

SGLang

TensorRT-LLM

Job description

adaption is seeking an experienced ML systems engineer to own the cost and performance of our inference stack, ensuring efficient model serving as workloads and hardware evolve. You will collaborate with the serving fleet to optimize caching, batching, quantization, decoding, and kernel-level tuning for higher throughput and lower latency without sacrificing reliability or model quality.

You will drive improvements in long-context prefill and decode workloads, optimize routing to external