Remote AI Optimization Engineer - Performance & Latency

Bright Vision Technologies; Artesia, Cerritos (CA, CA); Remote; USD 90,000 - 110,000; Full time

Job summary

Bright Vision Technologies is seeking an AI Optimization Engineer for a 100% remote role in the U.S. The engineer will optimize training and inference workflows for large neural networks, spanning kernel to distributed system tuning, with emphasis on throughput, latency, and cost.

Strong Python/C++ skills and GPU experience are required. Work closely with cross-functional teams, measure performance, and drive data-driven improvements.

Qualifications

• Bachelor's or Master's degree in Computer Science, Computer Engineering, or related field.
• 6+ years of experience in performance engineering, ML systems, or HPC.
• Strong proficiency in Python and C++.
• Hands-on experience optimizing deep learning workloads on modern GPUs.
• Deep understanding of distributed training and inference techniques.

Responsibilities

• Extract maximum throughput, minimize latency, and reduce cost across training and inference workloads for large neural networks.
• Span the full stack from low-level kernel optimization to distributed system tuning.
• Demonstrate impact on production AI workloads with instrumentation and data-driven optimization decisions.
• Collaborate with product, design, engineering, operations, and business to translate requirements into engineered solutions; mentor junior engineers.

Skills

Python

C++

Performance engineering

ML systems

HPC

Distributed training

Education

Bachelor's or Master's in CS/CE

Tools

TensorRT-LLM

DeepSpeed

Triton

CUTLASS

Job description

Bright Vision Technologies is seeking an AI Optimization Engineer for a 100% remote role in the U.S. The engineer will optimize training and inference workflows for large neural networks, spanning kernel to distributed system tuning, with emphasis on throughput, latency, and cost.

Strong Python/C++ skills and GPU experience are required. Work closely with cross-functional teams, measure performance, and drive data-driven improvements.