Remote AI Performance Engineer - Max Throughput

Bazeta; Northern (KY); Hybrid; USD 90,000 - 110,000; Full time

Job summary

Bright Vision Technologies is seeking an AI Optimization Engineer to maximize throughput, reduce latency, and lower costs across training and inference workloads for large neural networks. The role spans from kernel optimization to distributed system tuning.

The ideal candidate has 6+ years of performance engineering, strong Python and C++, and proven impact on production AI workloads, with excellent instrumentation and collaboration skills.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or related field.
• 6+ years in performance engineering, ML systems, or HPC.
• Strong Python and C++ proficiency.
• Experience optimizing DL workloads on modern GPUs.
• Knowledge of distributed training and inference techniques.
• Familiarity with profiling across CPU/GPU/distributed systems.
• Understanding of model compression and memory hierarchies.

Responsibilities

• Maximize throughput, minimize latency, and reduce cost for training/inference workloads.
• Profile and optimize kernel, memory, and communication paths across GPUs and CPUs.
• Collaborate with product, design, engineering, and operations to implement production-ready optimizations.
• Mentor junior engineers and contribute to design/review processes.

Skills

Python

C++

GPU optimization

ML systems

Distributed training

Profiling tools

Memory management

Measurement & debugging

Communication

Collaboration

Education

Bachelor’s or Master’s in CS/Engineering

Tools

Triton

CUTLASS

TensorRT-LLM

DeepSpeed

Job description

Bright Vision Technologies is seeking an AI Optimization Engineer to maximize throughput, reduce latency, and lower costs across training and inference workloads for large neural networks. The role spans from kernel optimization to distributed system tuning.

The ideal candidate has 6+ years of performance engineering, strong Python and C++, and proven impact on production AI workloads, with excellent instrumentation and collaboration skills.