Mlops Engineer - Ai Systems

Mercor; San Francisco (CA); Hybrid; GBP 93,000 - 124,000; Full time

Benefits offered by this job

Weekly payment via Stripe

Remote work

Job summary

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.

Qualifications

• 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.

Responsibilities

• 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.

Skills

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

Tools

JAX profiler

Nsight

Kineto

torch.profiler

CUDA tooling

Job description

About the job

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.

Position: MLOps Engineer, LLM Performance (Kernels, Profiling, Serving)
Type: Contract
Compensation: $90–$120/hour
Location: Remote
Commitment: 40 hours/week

Role Responsibilities

• Design challenging tasks across kernels, profiling, debugging, and inference serving. Write accurate, well-structured solutions to expose where frontier models fail on accelerator code.
• Guide research and engineering teams to close knowledge gaps and improve AI model performance on ML systems, compilers, and training infrastructure topics.
• Evaluate ML systems tasks and solutions. Provide clear written technical feedback that stands up to expert review.
• Develop guidelines and detailed rubrics covering kernel optimization, profiler output interpretation, distributed systems reasoning, and serving throughput and latency trade-offs.
• Collaborate with other subject matter experts to keep training data consistent and accurate.

Qualifications

Must-Have

• 2+ years of hands-on professional experience in ML systems, ML infrastructure, model serving, or accelerator performance engineering.
• Practical experience in writing or optimizing custom kernels (Pallas, Triton, CUDA, CUTLASS), performance profiling and trace analysis (JAX/XLA profiler, Kineto, torch.profiler, Nsight), debugging distributed or accelerator-bound workloads, serving large language models at scale (vLLM, SGLang, TensorRT-LLM, JetStream, KV cache, paged attention, continuous batching).
• Working production experience with JAX and/or PyTorch. Framework-level depth is a strong plus: custom operators, sharding and distributed training (pjit/shard_map, FSDP, Megatron, MaxText), or compiler and graph-level work (XLA/StableHLO, torch.compile, MLIR).
• Experience with modern accelerators such as TPU (v4 to v6e), H100, B200, Trainium or MI300, and the ability to reason about throughput, latency, and memory trade-offs.
• Demonstrable career progression.
• Ability to engage reliably for at least 40 hours/week during weekdays.
• Strong written communication skills and the ability to explain complex technical decisions clearly.

Compensation & Legal

• Hourly contractor
• Paid weekly via Stripe Connect

Resources & Support

• For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome
• For any help or support, reach out to: [e-mail]