Software Engineer - Model Serving Infrastructure

About Anyscale:At Anyscale, we're on a mission to democratize distributed computing and make it accessible to software developers of all skill levels. We’re commercializing Ray, a popular open-source project that's creating an ecosystem of libraries for scalable machine learning. Companies like OpenAI, Uber, Spotify, Instacart, and many more, have Ray in their tech stacks to accelerate the progress of AI applications out into the real world.With Anyscale, we’re building the best place to run Ray, so that any developer or data scientist can scale an ML application from their laptop to the cluster without needing to be a distributed systems expert.Proud to be backed by Andreessen Horowitz, NEA, and Addition with $250+ million raised to date.Anyscale is actively seeking talented engineers to join our team and contribute to the development of next-generation, high-performance machine learning serving systems. We value diversity and inclusion, and we encourage individuals from underrepresented groups to apply.Many existing ML serving tools are inherited from previous infrastructure generations, but emerging ML applications present new requirements, such as high compute demands, specialized hardware needs, and the integration of multiple models and business logic within a single request. At Anyscale, our mission is to provide a powerful yet simple set of tools that enable the seamless deployment of complex ML applications in production.The ChallengeWhat if you could build the infrastructure that powers AI applications for millions of users worldwide? Ray Serve is the production-grade serving framework that makes this possible—and we need exceptional engineers to push its boundaries.You'll be working on problems that sit at the intersection of distributed systems, machine learning, and high-performance computing. This isn't about maintaining CRUD apps or tweaking configurations—this is about solving fundamental computer science problems that directly impact how the world deploys AI.What You'll Actually Build:Problems We're Solving Right NowSub-millisecond Model Routing: Design and implement intelligent request routing systems that dynamically balance load across thousands of model replicas while maintaining strict latency SLAsZero-Downtime Model Updates: Build sophisticated traffic management systems that seamlessly transition between model versions at scale, handling terabytes of inference requests without dropping a single queryAutoscaling at Scale: Create reactive systems that predict traffic patterns and scale model replicas from 1 to 10,000+ instances based on real-time demand signalsMulti-Model Orchestration: Architect frameworks for complex ML pipelines where dozens of models need to communicate, share resources, and maintain end-to-end latency guaranteesObservability & Debugging: Build deep introspection tools that make it trivial to debug distributed ML applications—because "works on my laptop" doesn't cut it at scaleThe Tech You'll Work WithDeep Systems Programming: You'll write performance-critical code in Python (with Cython optimization paths) and potentially C++ for the hot pathsDistributed Systems at Scale: Work directly with Ray Core's actor system, gRPC, and custom networking protocols to handle millions of requests per secondCloud-Native Infrastructure: Kubernetes, service meshes, and custom operators—you'll need to understand and extend the cloud native ecosystemML/AI Systems: TensorFlow, PyTorch, JAX, transformers—you don't need to be an ML expert, but you'll develop deep knowledge of how these systems work under the hoodProduction Reliability: OpenTelemetry, Prometheus, distributed tracing, and chaos engineering to ensure 99.99% uptimeWhat We're Looking For:Must-HavesStrong Systems Fundamentals: You understand operating systems, networking, concurrency, and distributed systems at a deep levelProduction Experience: You've built and maintained systems that serve real users at scaleCode Quality: You write clean, tes ... (truncated, view full listing at source)