Applied AI Engineer, Inference

CoreWeave is The Essential Cloud for AI, a publicly traded company (Nasdaq: CRWV) delivering a platform for building and scaling AI. The Inference team is responsible for high-performance model serving. This Applied AI Engineer role focuses on understanding, measuring, and improving real-world performance of the inference platform, with initial responsibilities in benchmarking, optimization, and workload-driven research.

• Build and maintain benchmarking workflows measuring latency, throughput, quality regressions, and cost.
• Benchmark the inference stack against realistic customer workloads and external provider baselines.
• Profile model-serving behavior across frameworks, runtimes, and hardware to find bottlenecks in prefill, decode, KV cache usage, batching, graph capture, quantization, and related systems.
• Drive targeted optimizations for customer and product workloads, tuning serving configurations and validating changes.
• Design and run experiments on model-serving techniques such as quantization, speculative decoding, caching, and routing.
• Partner with inference platform engineers to productionize improvements and establish repeatable performance testing workflows.
• Produce technical writeups and recommendations on model configurations, runtime choices, hardware allocation, and deployment strategies.

• 4+ years of experience in machine learning, systems, performance engineering, or adjacent applied engineering work.
• Strong programming skills in Python and comfort in production engineering environments.
• Experience running empirical evaluations, benchmarks, or experiments and translating results into engineering decisions.
• Familiarity with LLM inference systems and tools such as vLLM, SGLang, TensorRT-LLM, or similar model-serving stacks.
• Understanding of tradeoffs in latency, throughput, batching, GPU utilization, quantization, and quality regression analysis.
• Ability to work across model, systems, and product boundaries.
• Strong written communication and a bias toward making technical work legible and reproducible.

The base salary range for this role is $188,000 to $275,000, determined by job-related knowledge, skills, experience, and market location. Total rewards include a discretionary bonus, equity awards, and a comprehensive benefits program. Benefits include medical, dental, and vision insurance (100% paid by CoreWeave), company-paid life insurance, short- and long-term disability insurance, tuition reimbursement, mental wellness benefits, family-forming support, paid parental leave, childcare support, 401(k) with employer match, flexible PTO, and catered lunch in office and data center locations.

This position requires access to export controlled information; applicants must be a U.S. person, eligible to access without authorization, or eligible and reasonably likely to obtain the required export authorization.