AI Performance Engineer

This role is part of Bright Vision Technologies’ in-house Statement of Work (SOW) engagement. The client, end customer, and employer for this position is Bright Vision Technologies - there is no third-party client, vendor, or implementation partner involved. We do not engage in C2C, 1099, or third-party arrangements for this role. BUT STRICTLY NO C2C/1099/3RD PARTY COMPANIES. ALL OUR ROLES ARE W2 AND NO 3RD PARTY BROKERING PLEASE. Candidates must be willing to work directly as a full-time W2 employee of Bright Vision Technologies and contribute to our in-house SOW deliverables. No new H1B sponsorship is available for this role. However, candidates who are currently on a valid H1B visa and require a transfer are welcome to apply. We will support H1B transfers for qualified candidates. For every role, a technical coding assessment is mandatory. Please apply only if you are confident in your technical abilities and hands-on experience., We are seeking an AI Performance Optimization Engineer to focus on extracting maximum throughput, minimizing latency, and reducing cost across training and inference workloads for large neural network systems. The role spans the full stack from low-level kernel optimization to distributed system tuning, requiring deep understanding of GPU architecture, model parallelism, memory management, and compiler-level optimization. The ideal candidate has demonstrated an impact on production of AI workloads, with strong instrumentation and measurement discipline that enables rigorous, data-driven optimization decisions. In this role you will work closely with cross-functional partners - product, design, engineering, operations, and business stakeholders - to translate ambiguous requirements into well-engineered solutions, and will be expected to raise the bar through code review, design review, and mentorship of more junior engineers. The successful candidate brings strong engineering discipline, a clear communication style, and a track record of shipping meaningful work that holds up well in production., * 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.
• Optimize distributed training using tensor parallelism, pipeline parallelism, FSDP, and ZeRO-style sharding.
• Tune attention implementations using Flash Attention, paged attention, and related techniques.
• Implement KV cache optimization, continuous batching, and speculative decoding for LLM serving.
• Drive compiler-level optimizations using Triton, XLA, Torch Inductor, or TVM, working with the broader ML framework community to land improvements that translate into measurable end-to-end performance gains.
• Optimize data pipelines, sharding strategies, and storage access patterns for high-throughput training.
• Build and maintain rigorous benchmark suites and regression frameworks across workloads.
• Collaborate with ML and platform engineering teams to embed best practices in standard pipelines.
• Drive cost-efficiency improvements 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 broadly across engineering teams.
• Stay current with AI systems to research and translate advances into production improvements.

• Bachelor’s or master’s degree in computer science, Computer Engineering, or 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.

Preferred Qualifications

• 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.

Salary Range: 100k$/Annum-150k$/Annum Location: 100% Remote (Continental United States) Position Type: In-house Bright Vision Technologies SOW engagement (no third-party client or vendor) Experience: 6+ years Sponsorship: No new H1B sponsorship available. H1B transfers welcomed for qualified candidates. Employment Type: Full-time, direct W2 with Bright Vision Technologies (no C2C, no 1099, no third-party) Engagement: Long-term, multi-year, aligned to the Bright Vision SOW delivery roadmap Compensation: Competitive base salary commensurate with experience, plus benefits. Employment Terms & Visa Policy

Bright Vision Technologies is a forward-thinking software development company dedicated to building innovative solutions that help businesses automate and optimize their operations. We leverage cutting-edge technologies to create scalable, secure, and user-friendly applications., Leviton Manufacturing

• Melville, NY About Leviton: At Leviton, we build what’s next to light, power, and connect everyday spaces, from electrical to lighting, to data networks, and energy management. With over 115 …