MLOps Engineer, LLM Performance (Kernels, Profiling, Serving) — Mercor

MLOps Engineer specializing in large language model optimization and deployment. This remote gig involves kernel tuning, performance profiling, and serving infrastructure work for advanced generative AI systems. You'll collaborate with a leading AI lab's research team to ensure LLMs run efficiently at scale, handling the technical backbone that powers model performance and reliability.

Best suited for engineers with solid systems-level coding experience and proven track record optimizing ML workloads. You should be comfortable diving into low-level performance analysis, containerization, and production serving frameworks. This is advanced AI infrastructure work—not entry-level—and requires hands-on familiarity with LLM deployment challenges.

Remote position available at $90–$120/hour, structured as a gig engagement. Expect roughly 40 hours per week.

Details: Advanced-level, data work, remote, listed pay $90 – $120/hour.