• We are looking for AI-first engineers who use Generative AI as a foundation of software engineering. • This role applies AI across the Product Development Lifecycle, from requirements and design to deployment and operations. • You will design and build AI Agents, apply prompting techniques, and implement architectures like RAG. • You will collaborate closely with product and engineering teams to embed AI into daily workflows. • Translate product and engineering challenges into AI solutions. • Build and deploy AI Agents with reasoning and memory integration. • Apply prompt engineering and RAG to real-world use cases. • Collaborate with teams to embed AI into requirements, coding, testing, and operations. • Prototype and test AI solutions, balancing experimentation with production readiness. • Support demonstrations of AI use cases for clients and internal stakeholders. • Stay current with advances in Generative AI and bring them into practice. • Communicate findings and trade-offs clearly in English to both technical and business audiences.

• Lead the design and implementation of complex ML/AI systems end-to-end, owning architecture decisions and driving solutions from research through production at scale • Build and evolve scalable ML platforms, pipelines, and infrastructure that support reliable, repeatable model development and deployment across teams • Set the standard for AI-forward engineering, using tools like Claude and Cursor with sophistication and helping the team adopt them effectively • Partner with product, engineering, and leadership to shape AI strategy and align technical direction with business outcomes • Translate complex AI tradeoffs, risks, and opportunities into clear narratives that drive decision-making across technical and non-technical stakeholders • Lead design reviews and technical discussions, raising the bar for engineering rigor and constructive challenge across the team • Define AI architecture and engineering standards, bringing depth on tradeoffs, long-term implications, and responsible AI practices • Mentor and grow junior and mid-level engineers, multiplying impact through coaching, code reviews, and pairing on hard problems • Take ownership of the most ambiguous and highest-stakes pieces of work, driving them through to production with care for reliability, cost, and safety.

• Own the end-to-end delivery of AI-powered applications • Partner with clients and internal stakeholders to define product requirements and delivery priorities • Translate business needs into actionable technical plans for engineering teams • Coordinate cross-functional teams to deliver AI solutions on time and with high quality • Leverage AI tools to improve planning, documentation, prototyping, and delivery workflows • Continuously identify opportunities to incorporate AI into products and internal processes • Track project progress, remove blockers, and communicate status to stakeholders • Drive rapid iteration and continuous improvement throughout the product lifecycle

Role Description 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. Key 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 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. Qualifications - 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. How to Apply Would you like to know more about this opportunity? For immediate consideration, please send your resume to [email protected] or contact us at (908) 650-6699. Learn more about Bright Vision Technologies at www.bvteck.com .