Remote AI Performance Engineer - Optimize ML Pipelines

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

Job summary

Bright Vision Technologies is seeking an AI Performance Engineer for 100% remote work in the U.S. The role requires 6+ years in performance engineering for ML systems, with strong Python/C++ and GPU optimization skills.

You will profile and optimize training/inference pipelines, implement quantization and pruning, and drive compiler-level improvements using Triton, XLA, TorchInductor, or TVM. Responsibilities include optimizing data loading, memory, and communication, plus collaboration with ML

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or related field.
• 6+ years in performance engineering, ML systems, or HPC.
• Strong proficiency in Python and C++ for ML workloads.
• Experience optimizing deep learning workloads on modern GPUs.

Responsibilities

• Profile and optimize end-to-end AI training and inference pipelines for throughput and latency.
• Identify bottlenecks across data loading, model compute, communication, and memory.
• Implement and tune quantization, sparsity, and pruning to reduce model footprint.
• Optimize distributed training using tensor parallelism, pipeline parallelism, FSDP, and ZeRO sharding.
• Tune attention with FlashAttention and related techniques; optimize KV cache and decoding.
• Drive compiler-level optimizations using Triton, XLA, TorchInductor, or TVM.
• Improve data pipelines, sharding, and storage for high throughput training.
• Build benchmark suites and regression frameworks across workloads.
• Collaborate with ML and platform teams to embed best practices in pipelines.
• Drive cost-efficiency via model architecture, hardware, and scheduling strategies.
• Evaluate new hardware/software offerings and advise adoption.
• Document performance tuning playbooks and share findings across teams.
• Stay current with AI systems research and translate advances to production.

Skills

Python

C++

Performance profiling

GPU optimization

Distributed training

ML systems

Education

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

Tools

TorchInductor

Triton

TVM

XLA

Job description

Bright Vision Technologies is seeking an AI Performance Engineer for 100% remote work in the U.S. The role requires 6+ years in performance engineering for ML systems, with strong Python/C++ and GPU optimization skills.

You will profile and optimize training/inference pipelines, implement quantization and pruning, and drive compiler-level improvements using Triton, XLA, TorchInductor, or TVM. Responsibilities include optimizing data loading, memory, and communication, plus collaboration with ML