Remote MLOps Engineer: LLM Performance & Serving

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

Vantaggi offerti da questo lavoro

Remote work

Descrizione del lavoro

Parailabs is seeking on a cutting-edge GenAI engineering role within our remote GenAI team. You will work on foundational AI models and large language model infrastructure, focusing on accelerator kernels, profiling, debugging, and high-throughput inference serving.

You will collaborate with researchers and engineers across ML systems, compilers, and training infrastructure, contributing to reliable model training and evaluation while operating as a fully remote contractor through

Competenze

• ;2+ years hands-on experience in ML systems, ML infrastructure, model serving, or accelerator performance engineering.

Mansioni

• Design tasks across kernels, profiling, debugging and inference serving.
• 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 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.

Conoscenze

Kernel programming

Performance profiling

Distributed systems

ML inference serving

JAX/PyTorch

TPU/accelerators

Strumenti

Kineto

torch.profiler

Nsight

JAX/XLA profiler

XLA

Descrizione del lavoro

Parailabs is seeking on a cutting-edge GenAI engineering role within our remote GenAI team. You will work on foundational AI models and large language model infrastructure, focusing on accelerator kernels, profiling, debugging, and high-throughput inference serving.

You will collaborate with researchers and engineers across ML systems, compilers, and training infrastructure, contributing to reliable model training and evaluation while operating as a fully remote contractor through