Senior AI Systems Performance Engineer - Remote

Triwill Group; United States; Remote; USD 130,000 - 180,000; Full time

Job summary

Bright Vision Technologies is seeking an experienced AI Systems Performance Specialist with 10+ years in AI infrastructure, HPC, and performance engineering. The role focuses on optimizing AI training and inference workloads for throughput, latency, scalability, and cost efficiency across enterprise-scale platforms.

The ideal candidate will have deep CUDA expertise, Python/C++, and a track record in GPU optimization, distributed training, and production AI systems.

Qualifications

• Bachelor's or Master's degree in CS/CE/EE/AI or a related field.
• 10+ years in performance engineering, AI infrastructure, HPC, or distributed computing.
• Expert-level Python and C++ programming.
• Experience optimizing GPU-accelerated AI workloads with CUDA and distributed training frameworks.
• Strong knowledge of LLMs, DL frameworks, and production AI inference.
• Experience profiling with Nsight, PyTorch Profiler, TensorBoard, or similar tools.

Responsibilities

• Optimize AI training and inference pipelines for throughput, latency, scalability, and cost efficiency.
• Analyze and improve GPU utilization, memory, kernel execution, and multi-GPU performance.
• Design optimization techniques: quantization, pruning, mixed precision, batching, caching, and model parallelism.
• Profile AI apps using industry-standard tools and identify bottlenecks across compute, memory, networking, and storage.
• Improve distributed training and inference with NCCL, DeepSpeed, PyTorch Distributed, Ray, MPI, etc.
• Collaborate with researchers, ML engineers, platform engineers, and infrastructure teams to boost performance and reliability.
• Build benchmarking frameworks, dashboards, monitoring, and regression testing pipelines.
• Evaluate new AI hardware and frameworks to improve enterprise AI capabilities.

Skills

Python

C++

GPU optimization

HPC

Distributed training

LLMs

Model serving

Profiling

Education

Bachelor's or Master's degree in CS/CE/EE/AI

Tools

NVIDIA Nsight Systems

Nsight Compute

PyTorch Profiler

TensorBoard

AWS

Azure

GCP

DeepSpeed

NCCL

Ray

MPI

CUDA

Job description

Bright Vision Technologies is seeking an experienced AI Systems Performance Specialist with 10+ years in AI infrastructure, HPC, and performance engineering. The role focuses on optimizing AI training and inference workloads for throughput, latency, scalability, and cost efficiency across enterprise-scale platforms.

The ideal candidate will have deep CUDA expertise, Python/C++, and a track record in GPU optimization, distributed training, and production AI systems.