Ml Infrastructure Expert - Fully Remote | Up To $120/Hr

Mercor

San Francisco (CA)

Hybrid

GBP 94,000 - 125,000

Full time

2 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Mercor is seeking an experienced MLOps Engineer, LLM Performance, to design and optimize kernel, profiling, and serving work across ML systems and hardware accelerators. You will guide teams to close knowledge gaps and improve AI model performance on high-end ML infrastructure.

The role is a remote contract with a 40-hour week commitment and compensation of $90–$120 per hour. Join a fast-paced team working with cutting-edge AI research platforms.

Qualifications

  • 2+ years hands-on experience in ML systems, ML infrastructure, model serving, or accelerator performance engineering.
  • Experience writing or optimizing custom kernels (Pallas, Triton, CUDA, CUTLASS) and profiling tools (JAX/XLA profiler, Kineto, torch.profiler, Nsight).
  • Production work with JAX and/or PyTorch; depth in compilers, graph work and distributed training is a strong plus.
  • Experience with modern accelerators (TPU, H100, Trainium, MI300) and throughput/latency trade-offs.
  • Strong written communication and ability to explain complex decisions; able to commit to 40 hours/week.

Responsibilities

  • Design tasks across kernels, profiling, debugging, and inference serving; expose failure modes on accelerator code.
  • Guide teams to improve AI model performance on ML systems, compilers, and training infra topics.
  • Evaluate ML system tasks; provide clear, expert-level technical feedback.
  • Develop guidelines and rubrics for kernel optimization, profiler outputs, and serving throughput/latency choices.
  • Collaborate to keep training data consistent and accurate.

Skills

ML systems
ML infrastructure
Model serving
Accelerator performance
CUDA
JAX
PyTorch
Distributed systems
Throughput optimization

Tools

Pallas
Triton
CUDA
CUTLASS
Kineto
Nsight
TensorRT-LLM

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
Application Process (Takes 20–30 mins to complete)
  • Upload resume
  • AI interview based on your resume
  • Submit form
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: support@mercor.com

PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Mlops Engineer - Ai Systems
Mlops Engineer - Ai Systems

Mercor • San Francisco (CA)

Hybrid
GBP 93,000 - 124,000
Weekly payment via Stripe
Remote work
MLOps Engineer - AI Systems
MLOps Engineer - AI Systems

Mercor • United States

Remote
USD 124,000 - 165,000
ML Challenge Task Auditor
ML Challenge Task Auditor

Mercor • Indiana

Hybrid
USD 96,000 - 124,000
ML Scientist | $90/hr
ML Scientist | $90/hr

Mercor • United States

Remote
USD 110,000 - 124,000
Ai Research Scientist - Fully Remote | Up To $200/Hr
Ai Research Scientist - Fully Remote | Up To $200/Hr

Mercor • San Francisco (CA)

Hybrid
GBP 154,000 - 205,000
ML Infrastructure and Performance Engineer, AI Expert (Remote)
ML Infrastructure and Performance Engineer, AI Expert (Remote)

Weekday AI • United States

Remote
USD 124,000 - 165,000
Expert Interviewer
Expert Interviewer

Mercor • United States

Remote
USD 69,000 - 83,000
GPU Kernel Expert
GPU Kernel Expert

Mercor • Indiana

Hybrid
USD 96,000 - 124,000
Referral reward
Remote work
Compliance Officer
Compliance Officer

Mercor • San Francisco (CA)

Remote
GBP 92,092 - 153,488
MLOps Engineer, LLM Performance (Kernels, Profiling, Serving)
MLOps Engineer, LLM Performance (Kernels, Profiling, Serving)

Parailabs • United States

Remote
USD 180,000 - 240,000
Remote work