Inference Engineer: High-Throughput ML Serving

Adaption Labs, Inc.; San Francisco (CA); Hybrid; USD 180,000 - 230,000; Full time

Benefits offered by this job

Flexible work: In-person collaboration

Adaption Passport

Lunch Stipend

Well-Being

Job summary

Adaption Labs, Inc. is seeking an ML systems engineer to own the cost and performance of the inference stack. You will optimize caching, batching, quantization, decoding, and kernel-level tuning to improve throughput and latency while preserving model quality.

You will collaborate with the serving fleet engineers and tackle real production workloads, focusing on cost-efficiency, tail latency, and reliable delivery across changing workloads and hardware. Bay Area presence required.

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

Python

Performance engineering

Tools

vLLM

SGLang

TensorRT-LLM

CUDA

Job description

Adaption Labs, Inc. is seeking an ML systems engineer to own the cost and performance of the inference stack. You will optimize caching, batching, quantization, decoding, and kernel-level tuning to improve throughput and latency while preserving model quality.

You will collaborate with the serving fleet engineers and tackle real production workloads, focusing on cost-efficiency, tail latency, and reliable delivery across changing workloads and hardware. Bay Area presence required.