Remote AI Performance Engineer: GPU & Inference Optimizer

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

Job summary

Bright Vision Technologies is seeking an AI Performance Engineer to optimize throughput and minimize latency for large neural network workloads across training and inference. You will work end-to-end from kernel optimization to distributed system tuning on GPUs, measuring impact with rigorous instrumentation.

The role requires strong Python/C++ skills and 6+ years in ML systems or HPC, plus experience with profiling, memory hierarchies, and model parallelism.

Qualifications

• Bachelor’s or Master’s degree in CS/CE or related field.
• 6+ years in performance engineering, ML systems or HPC.
• Proficiency in Python and C++.
• Experience optimizing DL workloads on modern GPUs.
• Understanding of distributed training and inference techniques.
• Experience with profiling tools across CPU, GPU, and distributed systems.
• Knowledge of memory hierarchies and parallelism.
• Strong measurement, debugging, and analytical skills.
• Excellent collaboration and communication.

Responsibilities

• Optimize throughput and latency for training and inference workloads.
• Work across the full stack from kernel level to distributed system tuning.
• Mentor junior engineers and participate in design and code reviews.
• Collaborate with product, design, engineering, operations and business teams.

Skills

Performance engineering

ML systems

Distributed training

Python

C++

Profiling tools

Memory optimization

Debugging

Communication

Education

Bachelor’s or Master’s in CS/CE or related field

Tools

Triton

CUTLASS

TensorRT-LLM

DeepSpeed

Job description

Bright Vision Technologies is seeking an AI Performance Engineer to optimize throughput and minimize latency for large neural network workloads across training and inference. You will work end-to-end from kernel optimization to distributed system tuning on GPUs, measuring impact with rigorous instrumentation.

The role requires strong Python/C++ skills and 6+ years in ML systems or HPC, plus experience with profiling, memory hierarchies, and model parallelism.