MLOps Engineer, LLM Performance: Kernels, Profiling, Serving (Remote, Full-time, AI lab project) — Mercor via AI Gig Scout

Mercor is looking for MLOps and ML systems engineers to join a leading AI lab's GenAI team, listed at $90–$120/hr. It is fully remote and open to candidates worldwide: depending on where you are based, you are engaged through Cincinnatus LLC or one of its employer-of-record partners, with placement at the lab as part of its extended workforce. It is a 40-hour full-time engagement with no other concurrent engagements.

The work centres on large language model infrastructure across four areas: accelerator kernel programming, performance profiling and trace analysis, debugging accelerated and distributed workloads, and high-throughput inference serving. You will design challenging tasks (including adversarial problems that expose where frontier models fail on accelerator code, for example Pallas kernels on TPU) and write solutions to them, evaluate ML systems tasks and solutions with clear written technical feedback, and develop guidelines and rubrics on kernel optimization, profiler output, distributed systems reasoning and serving throughput/latency trade-offs.

Requirements: 2+ years of hands-on professional experience in ML systems, ML infrastructure, model serving or accelerator performance engineering (a hands-on systems role, not applied modelling); practical experience in at least one of custom kernels (Pallas, Triton, CUDA, CUTLASS), profiling and trace analysis (JAX/XLA profiler, Kineto, torch.profiler, Nsight), debugging distributed or accelerator-bound workloads, or serving LLMs at scale (vLLM, SGLang, TensorRT-LLM, JetStream); production experience with JAX and/or PyTorch; experience with modern accelerators such as TPU, H100, B200, Trainium or MI300; availability for at least 40 hours a week on weekdays; strong written communication. JAX, XLA or TPU experience is especially valuable.

Details and apply link: https://aigigscout.com/jobs/mercor/mlops-engineer-llm-performance-kernels-profiling-serving-list-aaabowuvtb6qpgvqdb5nkon1?utm_source=kubernetesjobs&utm_medium=jobboard&utm_campaign=aigigscout_growth

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