AI Performance Engineer

Bright Vision Technologies•North Brunswick, NJ

2d•$100,000 - $150,000•Remote

About The Position

Bright Vision Technologies is seeking an AI Performance Optimization Engineer for a full-time, direct W2 position in its in-house Statement of Work (SOW) engagement. This is a 100% remote role for candidates in the continental United States, with no third-party client, vendor, or implementation partner involved. The engagement is described as long-term and multi-year. The salary range is $100,000–$150,000 per year, commensurate with experience, plus benefits. No new H1B sponsorship is available, but qualified candidates who require an H1B transfer are welcome to apply. A technical coding assessment is mandatory. The engineer will improve throughput, latency, and cost across training and inference workloads for large neural network systems. The work spans low-level kernel optimization through distributed-system tuning and calls for knowledge of GPU architecture, model parallelism, memory management, and compiler optimization. The role includes collaborating with product, design, engineering, operations, and business stakeholders to turn ambiguous requirements into well-engineered solutions. The engineer is also expected to contribute to code and design reviews and mentor more junior engineers, while delivering production-ready work with disciplined measurement and clear communication.

Requirements

Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
Six or more years of experience in performance engineering, ML systems, or HPC.
Strong proficiency in Python and C++.
Hands-on experience optimizing deep learning workloads on modern GPUs.
Deep understanding of distributed training and inference techniques.
Experience with profiling tools across CPU, GPU, and distributed systems.
Familiarity with model compression techniques and their accuracy implications.
Strong grasp of memory hierarchies, communication primitives, and parallelism strategies.
Excellent measurement, debugging, and analytical reasoning skills.
Strong communication and collaboration skills.
Willingness to work directly as a full-time W2 employee of Bright Vision Technologies and contribute to its in-house SOW deliverables.
Confidence in technical abilities and hands-on experience sufficient to complete a mandatory technical coding assessment.

Nice To Haves

Experience optimizing LLM inference at production scale.
Contributions to vLLM, TensorRT-LLM, DeepSpeed, or similar projects.
Familiarity with custom kernel authoring in Triton or CUTLASS.
Experience with FinOps for AI workloads.
Publications or talks on AI systems performance.

Responsibilities

Profile and optimize end-to-end AI training and inference pipelines for throughput, latency, and cost.
Identify and eliminate bottlenecks in data loading, model computation, communication, and memory.
Implement and tune quantization, sparsity, and pruning to reduce model footprint and accelerate inference.
Optimize distributed training using tensor parallelism, pipeline parallelism, FSDP, and ZeRO-style sharding.
Tune attention implementations using FlashAttention, paged attention, 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, collaborating with the broader ML framework community to achieve measurable end-to-end performance gains.
Optimize data pipelines, sharding strategies, and storage access patterns for high-throughput training.
Build and maintain benchmark suites and regression frameworks across workloads.
Collaborate with ML and platform engineering teams to embed best practices in standard pipelines.
Improve cost efficiency through model architecture, hardware selection, and scheduling strategies.
Evaluate new hardware and software offerings and advise on adoption.
Document performance-tuning playbooks and share findings across engineering teams.
Stay current with AI systems research and translate advances into production improvements.
Work with cross-functional partners to translate ambiguous requirements into well-engineered solutions.
Participate in code and design reviews and mentor more junior engineers.