Senior Inference Engineer, AIConfigurator for Dynamo

What you'll do

• Build and evolve AIConfigurator's core optimization engine for LLM serving.
• Develop Python/Rust APIs and CLIs to help users generate strong deployment configurations.
• Emit backend-specific artifacts for Dynamo, Kubernetes, TensorRT-LLM, vLLM, and SGLang deployments.
• Ensure simulated results match actual deployment performance on NVIDIA platforms.
• Improve model, hardware, and backend support by integrating various databases and tools.
• Convert complex inference ideas into reliable software abstractions.

What we're looking for

• 10+ years of relevant software engineering experience in production-quality Python/Rust development.
• Strong background in GPU computing and distributed systems for high-performance model serving.
• Deep understanding of LLM inference concepts including batching, latency, efficiency, and parallelism strategies.
• Experience with data-driven performance analysis, benchmarking, simulation, and optimization.
• Practical knowledge working directly with TensorRT-LLM, vLLM, SGLang, Triton Inference Server, or comparable platforms.
• Ability to collaborate across research, runtime, platform, and customer-facing engineering teams.