Remote ML Performance Engineer: Optimize Training Inference

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

Job summary

Bright Vision Technologies seeks an ML Performance Engineer to optimize large-scale AI workloads remotely in the U.S. The role spans kernel to distributed system tuning, requiring deep GPU architecture, memory management, and compiler optimization expertise.

The candidate will drive end-to-end performance improvements, collaborate across product and engineering, and mentor junior engineers while raising the bar with data-driven, measurable results.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or related field.
• Six or more years of performance engineering, ML systems, or HPC experience.
• Strong proficiency in Python and C++.
• Hands-on experience optimizing deep learning workloads on modern GPUs.
• Experience with profiling tools across CPU, GPU, and distributed systems.
• Familiarity with model compression techniques and their accuracy implications.
• Excellent measurement, debugging, and analytical reasoning skills.

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.
• Distributed training optimization using tensor/parallellism and ZeRO-style sharding.
• Tune attention implementations using FlashAttention and related techniques.
• Drive compiler-level optimizations using Triton, XLA, TorchInductor, or TVM.
• Collaborate with ML and platform teams to embed best practices in pipelines.
• Document performance tuning playbooks and share findings across engineering.

Skills

Python

C++

Distributed training

Profiling tools

GPU optimization

Benchmarking

Communication

Education

Bachelor’s or Master’s degree in Computer Science or Computer Engineering

Tools

Triton

XLA

TorchInductor

TVM

CUTLASS

Job description

Bright Vision Technologies seeks an ML Performance Engineer to optimize large-scale AI workloads remotely in the U.S. The role spans kernel to distributed system tuning, requiring deep GPU architecture, memory management, and compiler optimization expertise.

The candidate will drive end-to-end performance improvements, collaborate across product and engineering, and mentor junior engineers while raising the bar with data-driven, measurable results.