About Vercel:Vercel is the agentic infrastructure company. We free people and agents to ship what’s next. For more than a decade, Vercel has shaped how the web is built. As the team behind Next.js, v0, and AI SDK, we create products that help builders move from idea to production with speed, security, and exceptional developer experience. Now, software is entering a new era, and the next generation of products will not just be used by people. They will be built, extended, and operated by agents. We are building the platform for that future, trusted by companies like OpenAI, PayPal, Ramp, Supreme, and millions of developers worldwide. Whether you’re building our products, supporting our customers, growing our community, or shaping our story, you’ll help define what comes next. About the Role:Vercel is looking for engineers to help us build functional systems that improve product and customer experience. As a member of the Edge team, you will help to scale and improve our infrastructure, availability and reliability by working with our backend engineers and product team to identify problems, create tooling and automation. Your role will be dynamic - you should be comfortable designing systems, writing code, and debugging systems in production. Our team orchestrates deploying, routing and serving for our customers through capabilities and tooling we maintain that leverage our own and other cloud providers' infrastructure for networking, TLS termination, routing, storage, caching and other novel edge services. If you’re based within a pre-determined commuting distance of one of our offices (SF or NY), the role includes in-office anchor days on Monday, Tuesday, and Friday. If you're located beyond that distance, the role is fully remote. For location-specific details, please connect with our recruiting team. About You: - Intrigued about tackling the complex challenges serving petabytes of data and billions of requests to millions of people - A collaborative team player who believes in the power of strong teams to drive significant changes and innovations - Have at least 5 years of relevant experience - Have deep experience with how to make high performance systems scale in the cloud - Want to help protect the Vercel platform and our customers from abuse - Are keen to experiment, challenge norms and deliver secure and reliable systems that delight Vercel's users - Are knowledgeable and experienced with web servers, network protocols - Comfortable in Golang - Familiar with Cloud Services (e.g. AWS, Google Cloud, or others) - Experience with Terraform, Kubernetes, Lua, React and Next.js are nice-to-have! Benefits: - Competitive compensation package, including equity. - Inclusive Healthcare Package. - Learn and Grow - we provide mentorship and send you to events that help you build your network and skills. - Flexible Time Off. - We will provide you the gear you need to do your role, and a WFH budget for you to outfit your space as needed. The San Francisco, CA base pay range for this role is $196,000-$294,000. Actual salary will be based on job-related skills, experience, and location. Compensation outside of San Francisco may be adjusted based on employee location. The total compensation package may include benefits, equity-based compensation, and eligibility for a company bonus or variable pay program depending on the role. Your recruiter can share more details during the hiring process. Vercel is committed to fostering and empowering an inclusive community within our organization. We do not discriminate on the basis of race, religion, color, gender expression or identity, sexual orientation, national origin, citizenship, age, marital status, veteran status, disability status, or any other characteristic protected by law. Vercel encourages everyone to apply for our available positions, even if they don't necessarily check every box on the job description. #LI-DNI

• The primary responsibility of the Senior Software Engineer (AI-First Development) is to design, orchestrate, and validate software applications built through AI-driven development workflows. • This role operates within an AI-First Software Development Lifecycle (SDLC) where AI agents serve as the primary producers of code, configuration, and test artifacts. • The engineer provides architectural direction, context engineering, human-in-the-loop governance, and final accountability for all delivered software. • Combine deep software engineering fundamentals with the ability to think in systems, design effective agent workflows, and validate AI-generated outputs across security, correctness, performance, and compliance dimensions. • Design, build, and maintain AI agent workflows that produce application code, infrastructure configuration, test suites, and documentation. • Decompose complex application requirements into discrete tasks that AI agents can execute effectively. • Select and configure appropriate AI models, agent frameworks, and tooling for each workflow based on task complexity, risk level, and cost considerations. • Author and maintain the agent toolchain, including Skills (SKILL.md) for reusable domain knowledge, hooks for deterministic automation at defined workflow points, and project memory files (CLAUDE.md, AGENTS.md). • Review, test, and approve AI-generated code, ensuring it meets Sands coding standards, architectural guidelines, and security requirements before promotion to production. • Coordinate with development teams across global locations to ensure consistency in agent workflows and coding standards. • Evaluate emerging AI models, agent frameworks, and development tools to continuously improve workflow effectiveness and output quality.

• Direct the day-to-day technical execution of a small AI-First engineering team • Architect and deliver full-stack applications using AI-First methodologies • Define and maintain AI agent workflows • Collaborate with cross-functional teams to translate business requirements into executable workflows • Mentor team members on AI-assisted development practices

Role Description We're looking for a TPU and AMD GPU performance engineer to make vLLM a first-class inference engine across non-NVIDIA accelerators. Frontier inference cannot be locked to one hardware stack. As AMD GPUs, TPUs, and other accelerators become increasingly important, vLLM needs backend paths that are fast, correct, benchmarked, and maintainable across heterogeneous hardware platforms. - Build and optimize AMD GPU and TPU backends, kernels, compiler integrations, runtime paths, and benchmarking infrastructure. - Work at the boundary of inference systems, kernels, compilers, and hardware architecture. - Improve paths such as attention, GEMM, sampling, KV-cache, communication-heavy operations, and model serving on non-NVIDIA hardware. - Your work will directly impact how broadly and efficiently the world can run AI inference with vLLM. Qualifications - Bachelor's degree or equivalent experience in computer science, engineering, machine learning systems, hardware systems, compilers, or similar. - Hands-on experience optimizing workloads on AMD GPUs, TPUs, or another non-NVIDIA accelerator stack. - Experience with AMD ecosystem tools such as ROCm, HIP, Triton, CK, AITER, or equivalent GPU performance libraries and tooling. - Experience with TPU, XLA, JAX, Pallas, or related compiler and runtime tooling for accelerator workloads. - Ability to optimize ML inference paths such as attention, GEMM, sampling, KV-cache, fused kernels, backend runtimes, or communication-heavy operations. - Strong performance profiling and benchmarking discipline, including tokens/second, latency, throughput, correctness parity, hardware counters, and reproducible measurement methodology. - Ability to navigate immature tooling, incomplete documentation, backend-specific rough edges, and cross-platform performance differences without getting stuck. Requirements - Experience with vLLM, SGLang, TensorRT-LLM, ATOM, JAX-based serving framework, or other LLM inference systems. - Deep understanding of inference architecture and serving tradeoffs, including batching, KV-cache, decoding, prefill/decode scheduling, and backend performance constraints. - Experience with compiler technologies such as XLA, MLIR, LLVM, Triton, Pallas, or other compiler/kernel DSLs, including lowering, fusion, and backend code generation. - Knowledge of quantization techniques such as MXFP8, MXFP4, mixed precision, or hardware-specific numeric formats, and the ability to reason about accuracy/performance tradeoffs. - Experience with distributed inference performance, including communication, memory movement, hardware topology, and scale-out bottlenecks across multi-accelerator workloads. - Open-source contributions to vLLM, JAX/XLA, ROCm, Triton, PyTorch, compiler projects, or related ML systems infrastructure. Benefits - Generous health, dental, and vision benefits. - 401(k) company match. Logistics - Location: This role is based in San Francisco, California. Will consider remote in the US for exceptional candidates. - Compensation: Depending on background, skills, and experience, the expected annual salary range for this position is $200,000 - $400,000 USD + equity. - Visa sponsorship: We sponsor visas on a case-by-case basis.