Remote ML Performance Engineer – Scale AI Throughput

Bright Vision Technologies; Bothell (WA); On-site; USD 100,000 - 150,000; Full time

Job summary

Bright Vision Technologies is seeking an ML Performance Engineer for a 100% remote U.S. role that focuses on maximizing throughput, minimizing latency, and reducing costs across training and inference for large neural networks.

The position spans from low-level kernel work to distributed system tuning with a strong emphasis on measurable production impact. You will work with product and platform teams to drive end-to-end performance improvements, applying profiler tools and compiler backends

Qualifications

• Bachelor’s or Master’s degree in CS, CE, or related field.
• 6+ years in performance engineering, ML systems, or HPC.
• Strong proficiency in Python and C++.
• Experience optimizing deep learning workloads on modern GPUs.
• Deep understanding of distributed training and inference.
• Experience with profiling tools across CPU, GPU, and distributed systems.
• Familiarity with model compression techniques and accuracy implications.
• Strong memory hierarchy, communication primitives, and parallelism knowledge.
• Excellent measurement, debugging, and analytical reasoning skills.
• Strong communication and collaboration skills.

Responsibilities

• Profile and optimize AI training and inference pipelines for throughput, latency, and cost.
• Identify bottlenecks across data loading, model compute, communication, and memory.
• Implement and tune quantization, sparsity, and pruning strategies.
• Optimize distributed training using tensor parallelism, pipeline parallelism, FSDP, and ZeRO-style sharding.
• Tune attention implementations using FlashAttention and related techniques.
• Implement KV cache optimization, continuous batching, and speculative decoding for LLM serving.
• Drive compiler-level optimizations using Triton, XLA, TorchInductor, or TVM.
• Optimize data pipelines, sharding strategies, and storage access patterns.
• Build and maintain rigorous benchmark suites and regression frameworks.
• Collaborate with ML and platform teams to embed best practices.
• Drive cost-efficiency through model architecture, hardware selection, and scheduling.
• Evaluate new hardware and software offerings and advise on adoption.
• Document performance tuning playbooks and share findings widely.
• Stay current with AI systems research and translate advances into production improvements.

Skills

Python

C++

GPU optimization

Distributed training

Profiling tools

Model compression

Memory hierarchy

Education

Bachelor’s or Master’s in CS/CE

Tools

Triton

CUTLASS

TensorRT

DeepSpeed

Job description

Bright Vision Technologies is seeking an ML Performance Engineer for a 100% remote U.S. role that focuses on maximizing throughput, minimizing latency, and reducing costs across training and inference for large neural networks.

The position spans from low-level kernel work to distributed system tuning with a strong emphasis on measurable production impact. You will work with product and platform teams to drive end-to-end performance improvements, applying profiler tools and compiler backends