Remote MLOps Engineer for AI Systems (Contract, $90–$120)

Mercor; San Francisco (CA); Ibrido; GBP 93.000 - 124.000; Tempo pieno

Vantaggi offerti da questo lavoro

Weekly payment via Stripe

Remote work

Descrizione del lavoro

Mercor is hiring an MLOps Engineer, LLM Performance, to design kernel optimization, profiling, and inference serving tasks. The role guides teams to close knowledge gaps and improve AI model performance on ML systems, compilers, and training infrastructure topics.

You will collaborate with experts to ensure consistency and accuracy in training data, while delivering clear, expert-level feedback. The position is remote, hourly, and requires 40 hours/week commitment.

Competenze

• 2+ years of hands-on professional experience in ML systems, ML infrastructure, model serving, or accelerator performance engineering.
• Experience writing or optimizing custom kernels (Pallas, Triton, CUDA, CUTLASS).
• Production experience with JAX and/or PyTorch; knowledge of distributed training and compilers is a plus.
• Experience with modern accelerators (TPU, H100, MI300) and performance trade-offs.
• Ability to commit to 40 hours/week and communicate complex decisions clearly.

Mansioni

• Design tasks across kernels, profiling, debugging, and inference serving.
• Guide teams to improve AI model performance on ML systems and infra.
• Evaluate ML systems tasks and provide clear written feedback.
• Develop rubrics for kernel optimization, profiling, and serving latency.
• Collaborate with experts to keep training data consistent and accurate.

Conoscenze

ML systems

ML infrastructure

model serving

accelerator performance

kernels

profiling

CUDA

Pallas

Triton

JAX

PyTorch

XLA/StableHLO

Megatron

TensorRT-LLM

vLLM

SGLang

JetStream

KV cache

Strumenti

JAX profiler

Nsight

Kineto

torch.profiler

CUDA tooling

Descrizione del lavoro

Mercor is hiring an MLOps Engineer, LLM Performance, to design kernel optimization, profiling, and inference serving tasks. The role guides teams to close knowledge gaps and improve AI model performance on ML systems, compilers, and training infrastructure topics.

You will collaborate with experts to ensure consistency and accuracy in training data, while delivering clear, expert-level feedback. The position is remote, hourly, and requires 40 hours/week commitment.