Role Description vLLM is growing at a fast pace, and every bit of that growth lands on the CI system. More models, more hardware, more contributors, more ways for things to break. Your job is to make sure none of that slows anyone down. - Maintain and scale the compute infrastructure that powers CI, release, performance benchmark, accuracy evaluation for vLLM project, across a wide range of models and accelerators including H100/H200, (G)B200/300, AMD MI325/355X, TPU, Intel Gaudi, etc. - Get creative about cutting CI time-to-signal from hours to minutes. - Make sure every corner of vLLM code base is well-tested. - Keep vLLM releases rock-solid. - Build out tooling that helps 3,000+ vLLM contributors move fast. Qualifications - Strong experience with Docker, Kubernetes, and containerized build or test environments. - Built CI/CD pipelines from scratch using GitHub Actions, Buildkite, or similar systems. - Familiar with CI design patterns and CI techniques: compute orchestration, handling flaky tests, dependency/environment management, caching, remote execution, test target determination, etc., test coverage, and so on. - Fluent in Python, Bash, Go, or similar for automation and tooling. - Solid fundamentals of Linux, security, networking, storage, package management. Requirements - Bonus points for setting up infrastructure for ML, inference, CUDA, ROCm, or accelerator-heavy workloads. - Running Buildkite at scale, including agents, queues, dynamic pipelines, test sharding, caching, and artifact management. - Operating Kubernetes clusters for CI, batch jobs, test execution, or internal developer infrastructure. - Managing CI/CD in large open-source project. - Building dashboards, alerts, runbooks, or tooling for CI observability. Benefits - Generous health, dental, and vision benefits. - 401(k) company match.

Role Description We are looking for a Core Systems Engineer with a deep mastery of Rust to design, build, and optimize Sequen’s underlying model serving infrastructure and real-time performance engines. This role sits at the absolute core of our technical strategy. You will be responsible for ensuring our frontier ranking and recommendation APIs process petabyte-scale data and compute complex inference logic with ultra-low latency. You will replace high-overhead bottlenecks with elegant, production-grade Rust systems, building a reliable foundation that scales alongside our rapid enterprise customer growth. Responsibilities: - Optimize Real-Time Infrastructure: - Write high-performance, memory-safe, and concurrent production code in Rust. - Optimize model serving infrastructure to achieve ultra-low inference latency under heavy concurrent request loads. - Build low-latency data ingestion systems, microservices, and network protocols to process real-time behavioral streams. - Develop Core Architectural Tooling: - Design and maintain robust, high-throughput backend APIs and SDKs. - Implement customized abstractions, caching layers, and memory management profiles to maximize hardware efficiency. - Migrate data-heavy bottlenecks from higher-overhead languages into highly optimized Rust components. - Ensure Reliability and Scale: - Own the end-to-end lifecycle of core backend infrastructure components. - Debug complex distributed system deadlocks, race conditions, and production bottlenecks across cloud environments. - Establish rigorous performance benchmarking, regression testing, and real-time system monitoring. - Collaborate on Product Evolution: - Partner directly with Applied Scientists to translate recent neural network and ranking model breakthroughs into highly scalable runtime realities. - Define best practices for building secure, scalable, and deterministic system architectures across our entire engineering organization. Qualifications - 6 to 8+ years of experience in Software Engineering, Systems Programming, Infrastructure Engineering, or similar. - Strong professional experience writing and deploying production-grade Rust code in high-scale systems. - Deep understanding of Rust-specific primitives, including ownership, lifetimes, concurrency models, and asynchronous runtimes like Tokio. - Experience building robust backend systems, custom APIs, and event-driven architectures. - Experience debugging, profiling, and operating high-throughput production systems under strict real-world constraints. - Comfort with ambiguity, a strong sense of technical ownership, and an ability to balance engineering speed with quality. Requirements - Experience working with cloud platforms like AWS, GCP, or Azure and container orchestration tools like Docker and Kubernetes. - Experience implementing machine learning model inference optimizations, vector search databases, or large-scale data pipelines. - Background in early-stage startups or fast-moving, high-growth technical environments. Benefits At this stage, the efficiency and speed of our core infrastructure directly dictate how our product performs for global-scale consumer enterprises. You will have a blank canvas to architect core systems, work with bleeding-edge AI workflows, and fundamentally define the technical scalability of the company.

• Automate cloud infrastructure provisioning using Terraform and Ansible, writing IaC that supports Simple, Secure, and Scalable deployments • With an emphasis on networking, directly support platform engineering partners and application development teams in troubleshooting, provisioning and maintaining various enterprise infrastructure • Architect, optimize, and maintain secure network infrastructure in Azure, AWS, & GCP • Configure and manage virtual networks and subnets, including IP addressing, routing, firewall rules, and load balancing • Collaborate with security teams to enforce Zero Trust networking, IAM, and data encryption standards, as well as general security framework adherence • Through IPAM, maintain a network topology that provides for integration testing among development teams while remaining flexible enough to unify additional environments as merger and acquisition requires • Solution and implement Direct Connect, Express Route, and VPN technologies to establish secure, reliable and resilient connections • Work closely with Security and Compliance to ensure security framework adherence (SOC2, Hi-Trust, FEDRAMP etc.) • Provide self-service infrastructure governance and automation for the development teams, enabling them to focus on delivering business value as efficiently as possible

• Design and manage GCP project structure, networking, and core infrastructure • Own Kubernetes cluster infrastructure (provisioning, upgrades, scaling, reliability) • Define and maintain infrastructure-as-code (Terraform) standards and patterns • Improve system-level architecture for scalability, resilience, and performance • Build reusable infrastructure patterns that product teams can safely adopt • Reduce friction for developers while maintaining strong guardrails • Partner with engineering teams to improve how services are deployed and operated • Manage and evolve base observability systems (metrics, logging, tracing foundations) • Build and maintain infrastructure for secrets management, IAM, and security primitives • Ensure infrastructure is secure by default, not by exception • Improve infrastructure reliability and reduce systemic risk • Lead and contribute to incident response when infrastructure is involved • Identify and eliminate infrastructure-level failure modes and bottlenecks • Drive cloud cost visibility and optimization • Build systems and practices that balance performance, reliability, and cost • Partner with leadership to align infrastructure investment with business needs • Shape infrastructure strategy across teams and services • Drive adoption of standards and best practices across engineering • Identify systemic issues and lead cross-team improvements.