Remote AI Performance Engineer — Scale Production GPU DL

Bright Vision Technologies; Schaumburg (IL); Remote; USD 75,000 - 100,000; Full time

Job summary

Bright Vision Technologies is seeking an AI Performance Engineer to optimize throughput, reduce latency, and lower costs for large neural network workloads across training and inference. This role spans from kernel optimization to distributed system tuning, requiring deep GPU architecture and model parallelism knowledge.

You will collaborate with product, design, and engineering teams, drive data-driven decisions with instrumentation, and mentor junior engineers while delivering production-ready

Qualifications

• Bachelor’s or Master’s degree in CS/CE or related field.
• 6+ years in performance engineering, ML systems, or HPC.
• Strong Python and C++ proficiency.
• Hands-on optimization of DL workloads on modern GPUs.
• Understand distributed training and inference techniques.
• Experience with profiling tools across CPU, GPU, and distributed systems.
• Familiarity with model compression and its accuracy implications.
• Strong memory hierarchy, communication, and parallelism knowledge.
• Excellent measurement, debugging, and analytical skills.
• Strong communication and collaboration abilities.

Responsibilities

• Focus on maximizing throughput, minimizing latency, and reducing cost across training and inference workloads.
• Span from kernel optimization to distributed system tuning.
• Collaborate with product, design, and engineering teams to translate requirements into engineered solutions.
• Mentor junior engineers and contribute to code/design reviews.

Skills

Python

C++

Performance engineering

ML systems

GPU optimization

Profiling tools

Distributed training

Education

Bachelor’s or Master’s in CS/CE

Tools

TensorRT

Triton

CUTLASS

DeepSpeed

Job description

Bright Vision Technologies is seeking an AI Performance Engineer to optimize throughput, reduce latency, and lower costs for large neural network workloads across training and inference. This role spans from kernel optimization to distributed system tuning, requiring deep GPU architecture and model parallelism knowledge.

You will collaborate with product, design, and engineering teams, drive data-driven decisions with instrumentation, and mentor junior engineers while delivering production-ready