Applied AI Engineer (Inference)

Join our Inference team as an Applied AI Engineer, where you'll focus on improving the real-world performance of our inference platform. Your responsibilities will include building and running benchmarks, profiling model and system behavior, identifying bottlenecks, and driving targeted optimizations. You'll work closely with inference platform engineers and produce clear technical writeups to help the team make better decisions. This role requires strong programming skills in Python, experience in machine learning or performance engineering, and a curiosity about model behavior and systems architecture.

• Construire et maintenir des flux de travail de benchmarking qui mesurent la latence, le débit, les régressions de qualité et le coût.
• Profilage du comportement de service des modèles à travers les frameworks, les runtimes et les configurations matérielles pour trouver les goulets d'étranglement.
• Conduire des efforts d'optimisation ciblés pour des charges de travail spécifiques aux clients et aux produits, y compris le réglage des configurations de service.

• Strong written communication and a bias toward making technical work legible and reproducible for others
• Understanding of the practical tradeoffs involved in latency, throughput, batching, GPU utilization, quantization, and quality regression analysis
• Familiarity with LLM inference systems and tools such as vLLM, SGLang, TensorRT-LLM, or similar model-serving stacks
• 4+ years of experience in machine learning, systems, performance engineering, or adjacent applied engineering work
• Experience running empirical evaluations, benchmarks, or experiments and translating results into concrete engineering decisions
• Ability to work across model, systems, and product boundaries and stay focused on outcomes that matter for customers
• Strong programming skills in Python and comfort working in production engineering environments
• 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. Here are a few qualities we’ve found compatible with our team. If some of this describes you, we’d love to talk
• You’re an expert in running disciplined experiments and using data to drive practical performance improvements
• You love turning ambiguous performance problems into concrete measurements and engineering plans
• You’re curious about how model behavior, systems architecture, and hardware choices interact in production inference workloads
• This position requires access to export controlled information. To conform to U.S. Government export regulations applicable to that information, applicant must either be (A) a U.S. person, defined as a (i) U.S. citizen or national, (ii) U.S. lawful permanent resident (green card holder), (iii) refugee under 8 U.S.C. § 1157, or (iv) asylee under 8 U.S.C. § 1158, (B) eligible to access the export controlled information without a required export authorization, or (C) eligible and reasonably likely to obtain the required export authorization from the applicable U.S. government agency. CoreWeave may, for legitimate business reasons, decline to pursue any export licensing process
• Experience with profiling tools such as Nsight Systems, PyTorch profilers, or custom telemetry pipelines
• Familiarity with benchmark suites and evaluation frameworks for coding, reasoning, or agent workloads
• Experience optimizing inference workloads on modern GPU hardware
• Experience using real production traces or customer traffic patterns to guide optimization work
• Experience balancing model quality and serving performance when evaluating quantization, speculative decoding, or other acceleration strategies