Remote AI Systems Performance Architect

Bright Vision Technologies; Chapel Hill (NC); On-site; USD 130,000 - 180,000; Full time

Job summary

Bright Vision Technologies is seeking an AI Systems Performance Specialist with over a decade of experience in AI infrastructure, HPC, and performance engineering. The role focuses on optimizing training and inference workloads, GPU utilization, and scalable production AI systems.

The candidate will lead performance initiatives, work with researchers and platform engineers, and drive cost-efficient AI deployments across enterprise-scale platforms.

Qualifications

• 10+ years of professional experience in performance engineering, AI infrastructure, ML systems, HPC, or distributed computing.
• Expert-level Python and C++ programming.
• Experience optimizing GPU-accelerated AI workloads using CUDA and distributed training frameworks.
• Strong knowledge of LLMs, DL frameworks, model serving, and production AI inference.

Responsibilities

• Optimize AI training and inference pipelines for throughput, latency, scalability, and cost efficiency.
• Analyze and improve GPU utilization, memory management, and multi-GPU performance.
• Design and implement optimization techniques: quantization, pruning, mixed precision, batching, caching, speculative decoding, model parallelism.
• Profile AI apps with industry tools and identify bottlenecks across compute, memory, networking, storage.
• Drive distributed training and inference with NCCL, DeepSpeed, PyTorch Distributed, Ray, MPI, etc.
• Mentor teams and provide leadership on AI systems architecture and GPU optimization.

Skills

Python

C++

GPU optimization

Performance engineering

Distributed training

Analytics

Education

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

Tools

NVIDIA Nsight Systems

Nsight Compute

PyTorch Profiler

TensorBoard

Job description

Bright Vision Technologies is seeking an AI Systems Performance Specialist with over a decade of experience in AI infrastructure, HPC, and performance engineering. The role focuses on optimizing training and inference workloads, GPU utilization, and scalable production AI systems.

The candidate will lead performance initiatives, work with researchers and platform engineers, and drive cost-efficient AI deployments across enterprise-scale platforms.