Remote ML Performance Engineer — GPU & LLM Optimizer

Bright Vision Technologies; Sugar Land (TX); Remote; USD 100,000 - 150,000; Full time

Job summary

Bright Vision Technologies is seeking an AI Performance Optimization Engineer to maximize throughput, reduce latency, and cut cost across training and inference workloads for large neural networks. You will work from kernel optimization to distributed system tuning, with deep GPU, memory, and compiler expertise.

Collaboration with product, design, and operations teams is essential to translate requirements into production-grade solutions.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or related field.

Responsibilities

• Profile and optimize end-to-end AI training and inference pipelines for throughput, latency, and cost.
• Identify and eliminate bottlenecks across data loading, model compute, communication, and memory.
• Implement and tune quantization, sparsity, and pruning strategies to reduce model footprint and accelerate inference.
• Drive distributed training using tensor parallelism, pipeline parallelism, FSDP, and ZeRO-style sharding.
• Tune attention implementations using FlashAttention, paged attention, and related techniques.
• Drive compiler-level optimizations using Triton, XLA, TorchInductor, or TVM.
• Collaborate with ML and platform engineering teams to embed best practices in standard pipelines.
• Document performance tuning playbooks and share findings broadly across engineering teams.

Skills

Python

C++

Profiling tools

Distributed training

GPU architectures

Education

Bachelor's or Master’s degree in CS or related field

Tools

Triton

XLA

TorchInductor

TVM

FlashAttention

Job description

Bright Vision Technologies is seeking an AI Performance Optimization Engineer to maximize throughput, reduce latency, and cut cost across training and inference workloads for large neural networks. You will work from kernel optimization to distributed system tuning, with deep GPU, memory, and compiler expertise.

Collaboration with product, design, and operations teams is essential to translate requirements into production-grade solutions.