Job Summary:
NVIDIA is a leader in computer graphics and AI technology, seeking a Senior Compiler Engineer with expertise in compiler technologies. The role involves driving innovative solutions in compilers and developer tools through applied machine learning and AI, focusing on building AI-driven compiler intelligence for production pipelines.
Responsibilities:
• Join a team driving innovative solutions in compilers and developer tools through applied machine learning and AI.
• Collaborate with world-class engineers to shape next-generation compiler capabilities that power large-scale, high-impact products.
• Design and implement end-to-end compiler optimization workflows, from feature engineering and model development to compiler integration and production rollout.
• Develop and integrate learning-based decision systems into compiler passes, code generation flows, and optimization pipelines.
• Build robust interfaces between LLM systems and compiler infrastructure for optimization recommendations, decision support, and workflow automation.
• Partner with compiler, architecture, and performance teams to validate impact on representative workloads and benchmark suites.
• Lead experimentation, evaluation, and deployment with strong standards for reliability, scalability, and performance.
Qualifications:
Required:
• BS/MS/PhD in Computer Science or a related field (or equivalent experience), with a focus on machine learning and compiler/developer tools.
• 8+ years of software engineering and AI/ML experience, preferably in tools or systems development.
• Strong knowledge of compilers, code generation, and GPU architecture.
• Demonstrated proficiency in Python and C/C++.
• Strong mathematical and scientific foundation relevant to AI/ML and compiler technologies.
• Hands-on experience with LLVM/MLIR-based compiler development, including optimization passes, code generation, or frontend integration.
• Experience building or integrating LLM-based systems, agents, or developer tooling in production environments.
Preferred:
• Deep familiarity with reinforcement learning, genetic/evolutionary algorithms, predictive modeling, and complex systems.
• Proven track record of deploying AI/ML solutions in production and embedded environments.
• Strong experience integrating LLMs into systems workflows with attention to reliability, latency, and evaluation quality.
• Demonstrated measurable outcomes such as runtime gains, compile-time improvements, or efficiency improvements on real-world workloads.
• Publications, open-source contributions, or patents in compilers, AI/ML systems, or performance engineering.
Company:
NVIDIA is a computing platform company operating at the intersection of graphics, HPC, and AI. Founded in 1993, the company is headquartered in Santa Clara, USA, with a team of 10001+ employees. The company is currently Late Stage.