Senior Research Engineer, Enterprise Products

What you'll do

• Design and evaluate routing policies for LLM traffic to optimize mixture of model systems.
• Build and run agentic benchmarks to measure algorithm quality.
• Convert benchmark results into calibration data and routing profiles.
• Ship design documents, code, and documentation to an open-source repository.
• Contribute to the open-source community through code reviews and technical contributions.
• Integrate software seamlessly across the NVIDIA accelerated serving stack.
• Form hypotheses about new algorithms and iterate on results through empirical research.

What we're looking for

• Bachelor's or Master's degree in Computer Science or equivalent experience.
• 8+ years of industry experience in Deep Learning frameworks like PyTorch or TensorFlow.
• Experience designing or running LLM evaluations and benchmarks, specifically agentic ones.
• Understanding of modern techniques in Machine Learning, Deep Neural Networks, NLP, or Speech Recognition.
• Strong computer science fundamentals in algorithms, data structures, computational complexity, and parallel/distributed computing.
• Strong communication and interpersonal skills with the ability to work in a dynamic, distributed team.
• Experience architecting or developing large-scale distributed systems for deep learning (preferred).
• Knowledge of CPU/GPU architecture and GPU programming (CUDA) (preferred).