Remote MLOps Engineer — LLM Performance & Inference

Zekai; United States; Remoto; USD 180.000 - 240.000; Tempo pieno

Descrizione del lavoro

Zekai is seeking a remote MLOps/ML systems engineer to help build and optimize large language model infrastructure. The role focuses on accelerator kernels, profiling, debugging, and high-throughput inference serving, with hands-on work in JAX, XLA, and related tooling.

Candidates join through Cincinnatus LLC or trusted EOR partners, in a 40-hour weekly, fully remote engagement. Experience with JAX, PyTorch, and accelerator hardware (TPU, H100, etc.) is valued.

Competenze

• 2+ years of hands-on professional experience in ML systems, ML infrastructure, model serving, or accelerator performance engineering.
• Experience with building or optimizing ML systems, compilers, training infrastructure or serving large language models at scale is a strong plus.
• Strong written communication skills and the ability to explain complex technical decisions clearly.

Mansioni

• Design tasks across kernels, profiling, debugging and inference serving for frontier models.
• Guide research and engineering teams to close knowledge gaps and improve AI model performance on ML systems.
• Evaluate ML systems tasks and provide clear technical feedback.
• Develop guidelines and rubrics for kernel optimization, profiler outputs, distributed systems reasoning, and serving latency trade-offs.
• Collaborate with subject matter experts to maintain training data consistency.

Descrizione del lavoro

Zekai is seeking a remote MLOps/ML systems engineer to help build and optimize large language model infrastructure. The role focuses on accelerator kernels, profiling, debugging, and high-throughput inference serving, with hands-on work in JAX, XLA, and related tooling.

Candidates join through Cincinnatus LLC or trusted EOR partners, in a 40-hour weekly, fully remote engagement. Experience with JAX, PyTorch, and accelerator hardware (TPU, H100, etc.) is valued.