Remote AI Performance Engineer - Scale ML Inference

United States Digital Space LLC; United States; Remote; USD 75,000 - 100,000; Full time

Job summary

BV Teck is seeking an AI Performance Engineer for a 100% Remote role in the United States. The position focuses on extracting maximum throughput, minimizing latency, and reducing cost across training and inference workloads for large neural network systems.

This role spans from low-level kernel optimization to distributed system tuning, demanding deep GPU architecture and compiler-level optimization expertise.

Qualifications

• Bachelor's or Master's degree in Computer Science, Computer Engineering, or related field.
• Six+ years of experience in performance engineering, ML systems, or HPC.
• Strong proficiency in Python and C++.

Responsibilities

• Extract maximum throughput and minimize latency for training and inference workloads.
• Tune and optimize large neural network systems across full stack from kernel to distributed systems.
• Collaborate with cross-functional teams and mentor junior engineers.

Skills

Python

C++

GPU profiling

Distributed training

Memory hierarchies

Debugging

Collaboration

Education

Bachelor's or Master's degree in CS/CE

Tools

TensorRT

DeepSpeed

Triton

CUTLASS

vLLM

Job description

BV Teck is seeking an AI Performance Engineer for a 100% Remote role in the United States. The position focuses on extracting maximum throughput, minimizing latency, and reducing cost across training and inference workloads for large neural network systems.

This role spans from low-level kernel optimization to distributed system tuning, demanding deep GPU architecture and compiler-level optimization expertise.