Software/ML Engineer, LLM Inference & GPU Performance Evaluation (Remote, Contract, $125/hr) — AfterQuery via AI Gig Scout

AfterQuery is assembling a group of senior software and ML engineers, as remote contractors listed at $125/hr, to work on a hard open problem in AI: how well frontier models reason about LLM inference systems, GPU-level performance optimization and model-serving architecture. You will help design evaluation scenarios, write reference solutions and grade model outputs on real systems-engineering problems. It is a research-and-evaluation role, not shipping production code.

What you will do: design realistic technical scenarios and problem sets in LLM inference optimization, GPU kernel design and systems performance engineering, and define what correct and excellent look like for AI models tackling them.

Requirements: a Bachelor's or higher in Computer Science, Computer Engineering, Electrical Engineering or a related field; a strong hands-on background in one or more of GPU inference optimization, custom CUDA kernels, model-serving systems (vLLM, TensorRT-LLM, SGLang), quantization or optimizer design; experience at a recognized technology or AI company with real systems-engineering ownership; and strong written communication. Preferred: SGLang, Mamba/Mamba2 or IBM Granite experience, open-source contributions to inference frameworks, and distributed inference (tensor/expert parallelism, continuous batching, KV-cache optimization).

Details and apply link: https://aigigscout.com/jobs/afterquery/software-ml-engineer-senior-swe?utm_source=kubernetesjobs&utm_medium=jobboard&utm_campaign=aigigscout_growth

Disclosure: posted by AI Gig Scout, an independent listing site (not AfterQuery). The apply link may be a referral link.