Remote MLOps Engineer: LLM Performance & Kernels

Mercor

United States

Remote

USD 124,000 - 165,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Mercor is seeking an MLOps Engineer focusing on LLM performance, kernels, profiling, and serving. This remote contract role requires 40 hours per week and involves evaluating ML systems, optimizer kernel work, and collaboration with research and engineering teams to improve AI model performance on ML systems and training infrastructure.

The ideal candidate has hands-on ML systems experience, CUDA/TensorRT kernel work, and strong communication skills to clearly explain complex technical decisions

Qualifications

  • 2+ years of hands-on experience in ML systems, ML infrastructure, model serving, or accelerator performance engineering.
  • Proven ability to write or optimize custom kernels (CUDA/TensorRT) and perform performance profiling and trace analysis (JAX/XLA profiler, Kineto, torch.profiler, Nsight).
  • Experience with distributed or accelerator-bound workloads and serving large language models at scale (e.g., vLLM, TensorRT-LLM, KV cache, paged attention).
  • Working production experience with JAX and/or PyTorch.
  • Deep knowledge of modern accelerators (TPU v4-v6e, H100, Trainium, MI300) and ability to reason about throughput and latency.
  • Strong written communication skills and ability to explain complex technical decisions clearly.

Responsibilities

  • Design tasks across kernels, profiling, debugging, and inference serving.
  • Provide accurate, well-structured solutions to expose frontier model failures on accelerator code.
  • Guide research and engineering teams to improve AI model performance on ML systems and training infrastructure.
  • Evaluate ML systems tasks and solutions.
  • Provide clear written technical feedback suitable for expert review.
  • Develop guidelines and rubrics for kernel optimization, profiler outputs, and serving throughput/latency trade-offs.
  • Collaborate with SMEs to maintain training data consistency and accuracy.

Skills

ML systems
Kernel optimization
Performance profiling
Distributed workloads
JAX/PyTorch
CUDA/TensorRT
LLM serving
vLLM

Tools

Kineto
Nsight
Torch.profiler
XLA

Job description

Mercor is seeking an MLOps Engineer focusing on LLM performance, kernels, profiling, and serving. This remote contract role requires 40 hours per week and involves evaluating ML systems, optimizer kernel work, and collaboration with research and engineering teams to improve AI model performance on ML systems and training infrastructure.

The ideal candidate has hands-on ML systems experience, CUDA/TensorRT kernel work, and strong communication skills to clearly explain complex technical decisions

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

MLOps & LLM Performance Engineer — Remote
MLOps & LLM Performance Engineer — Remote

Mercor • San Francisco (CA)

Hybrid
GBP 94,000 - 125,000
Remote MLOps Engineer for AI Systems (Contract, $90–$120)
Remote MLOps Engineer for AI Systems (Contract, $90–$120)

Mercor • San Francisco (CA)

Hybrid
GBP 93,000 - 124,000
Weekly payment via Stripe
Remote work
Remote LLM Performance MLOps Engineer (Kernels, Serving)
Remote LLM Performance MLOps Engineer (Kernels, Serving)

AuraOne Human Data • United States

Remote
USD 124,000 - 165,000
MLOps Engineer - AI Systems
MLOps Engineer - AI Systems

Mercor • United States

Remote
USD 124,000 - 165,000
Remote MLOps Engineer: LLM Performance & Serving
Remote MLOps Engineer: LLM Performance & Serving

Parailabs • United States

Remote
USD 180,000 - 240,000
Remote work
Remote MLOps Engineer — LLM Performance & Inference
Remote MLOps Engineer — LLM Performance & Inference

Confidential • United States

Remote
USD 180,000 - 240,000
Mlops Engineer - Ai Systems
Mlops Engineer - Ai Systems

Mercor • San Francisco (CA)

Hybrid
GBP 93,000 - 124,000
Weekly payment via Stripe
Remote work
Ml Infrastructure Expert - Fully Remote | Up To $120/Hr
Ml Infrastructure Expert - Fully Remote | Up To $120/Hr

Mercor • San Francisco (CA)

Hybrid
GBP 94,000 - 125,000
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
MLOps Engineer, LLM Performance (Kernels, Profiling, Serving)
MLOps Engineer, LLM Performance (Kernels, Profiling, Serving)

AuraOne, Inc. • United States

Remote
USD 124,000 - 165,000