Remote AI Performance Engineer (Optimization & Throughput)

Bright Vision Technologies; Mountain View (CA); On-site; USD 85,000 - 115,000; Full time

Job summary

Bright Vision Technologies is seeking an AI Optimization Engineer to optimize throughput, latency, and cost across training and inference workloads for large neural networks. The role spans from low-level kernel optimization to distributed system tuning, requiring deep GPU architecture knowledge and measurement-driven decision making.

The ideal candidate will have 6+ years' experience in ML systems or HPC, strong Python/C++ skills, and a proven track record shipping production AI workloads.

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.
• Experience with profiling tools across CPU, GPU, and distributed systems.
• Familiarity with model compression techniques and their accuracy implications.
• Strong grasp of memory hierarchies, communication primitives, and parallelism.
• Excellent measurement, debugging, and analytical reasoning skills.
• Strong communication and collaboration skills.

Responsibilities

• Optimize throughput, minimize latency, and reduce cost across training and inference workloads for large neural networks.
• Tuning from low-level kernel optimization to distributed system optimization.
• Work with cross-functional teams to translate requirements into engineered solutions.
• Mentor junior engineers and contribute to design and code reviews.

Education

Bachelor’s or Master’s degree in Computer Science or Computer Engineering

Tools

Triton kernel

CUTLASS kernels

TensorRT-LLM

DeepSpeed

Job description

Bright Vision Technologies is seeking an AI Optimization Engineer to optimize throughput, latency, and cost across training and inference workloads for large neural networks. The role spans from low-level kernel optimization to distributed system tuning, requiring deep GPU architecture knowledge and measurement-driven decision making.

The ideal candidate will have 6+ years' experience in ML systems or HPC, strong Python/C++ skills, and a proven track record shipping production AI workloads.