Sr. Software Engineer, Inference

CoreWeave is The Essential Cloud for AI™. Built for pioneers by pioneers, CoreWeave delivers a platform of technology, tools, and teams that enables innovators to build and scale AI with confidence. Trusted by leading AI labs, startups, and global enterprises, CoreWeave combines superior infrastructure performance with deep technical expertise to accelerate breakthroughs and turn compute into capability. Founded in 2017, CoreWeave became a publicly traded company (Nasdaq: CRWV) in March 2025. Learn more at www.coreweave.com . We're proud to be a Living Wage accredited Employer. Senior Software Engineer, Inference Location: Warsaw, Poland What You'll Do: CoreWeave’s Inference team builds and operates the core cloud platform powering massive-scale GPU workloads for generative AI and real-time inference applications. Our stack is engineered natively on Kubernetes for maximum speed, scale, and cost efficiency—providing an industry-defining platform that enables teams to deploy models with confidence across organizational boundaries. About the role: As a Senior Software Engineer, Inference, you will serve as an area owner responsible for leading technical designs, raising engineering standards, and delivering measurable improvements across multiple services. You will partner with product, orchestration, and hardware teams to evolve our Kubernetes-native inference platform while meeting strict P99 SLAs at scale. In this role, you will lead design reviews, decompose multi-service work into clear milestones, and own critical infrastructure areas such as request routing, adaptive scheduling, cost-per-token analytics, and GPU resource isolation. Additionally, you will implement advanced optimizations—including micro-batch schedulers, speculative decoding, and KV-cache reuse—while refining capacity planning, autoscaling policies, and mentoring engineers across the team. Who You Are: Bachelor’s or Master’s degree in Computer Science or a related technical field (or equivalent practical experience). 3+ years of professional industry experience building distributed systems or high-performance cloud services. Strong software development skills in Python or Go, alongside deep familiarity with networked systems and performance optimisation. Hands-on experience with Kubernetes at production scale, including automated CI/CD and modern observability stacks (e.g., Prometheus, Grafana, OpenTelemetry). Practical, working knowledge of inference internals: batching strategies, caching, mixed precision (BF16/FP8), and streaming token delivery. Proven track record of improving tail latency (P95/P99) and service reliability through metrics-driven engineering work. Experience defining and owning SLIs/SLOs, managing capacity planning, autoscaling policies, and driving post-incident remediation. Preferred: Experience with low-level systems and high-performance computing components (e.g., C++ development, CUDA kernels, NCCL/SHARP, RDMA/NUMA, or GPU interconnect topologies). Active open-source or production contributions to modern inference frameworks (e.g., vLLM, Triton, TensorRT-LLM, Ray Serve, or TorchServe). Experience leading multi-team technical initiatives or partnering directly with enterprise customers on mission-critical platform launches. Wondering if you're a good fit? We believe in investing in our people, and value candidates who can bring their own diversified experiences to our teams—even if you aren't a 100% skill or experience match. You love to: Own critical architectural spaces, breaking down complex multi-service engineering work into high-impact, achievable milestones. You're curious about: Pioneering advanced model serving optimisations to maximise platform throughput and drive cost-per-token efficiencies. You're an expert in: Metrics-driven engineering, systematically troubleshooting tail latency bottlenecks, and elevating coding and testing standards across a team. Why CoreWeave? At CoreWeave, we work hard, have fun, and move fast! W…