Senior Architect, Model Performance and Post-Training

Start free →

Or apply yourself on the official page →

About the role

NVIDIA is widely regarded as one of the technology industry’s most desirable employers. We lead the way in High-Performance Computing, Artificial Intelligence, and Visualization. Our core invention, the GPU, serves as the visual cortex of modern computers and powers our entire product suite. GPU deep learning ignited the modern AI era—the next great computing age—with the GPU acting as the brain for everything from robots and autonomous cars to conversational AI. Today, we are known globally as "the AI computing company." We are looking to grow our teams by bringing in the smartest people in the world. Join us at the forefront of technological advancement. We are looking for a Senior Engineer to drive the performance modeling, evaluation, and post-training of large language models specialized in code generation, software engineering, and agentic coding tasks. In this role, you will work at the intersection of model training, inference optimization, and empirical analysis to improve coding model capabilities, efficiency, reliability, and real-world developer productivity. You will design experiments to understand model behavior, identify performance bottlenecks, and develop post-training strategies that translate into measurable improvements on coding benchmarks and real-world software engineering tasks. You will collaborate closely with research scientists, infrastructure engineers, and product teams to turn model insights into production-ready capabilities. What you'll be doing: • Develop meticulous frameworks to measure and analyze coding model performance across code generation, debugging, code completion, repository-level reasoning, and multi-step software engineering tasks. • Develop, and optimize post-training pipelines for coding models, including supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL), and outcome-based or process-based reward modeling. • Analyze benchmark results, training dynamics, failure modes, and model behaviors to find opportunities for improvement. • Improve model performance on sophisticated coding tasks through targeted training interventions, reward design, curriculum development, and iterative error analysis. • Build scalable, reproducible infrastructure for training experiments, evaluation pipelines, and model performance analysis. What we need to see: • Bachelor's degree (or equivalent experience) in Computer Science or AI with 12+ years of meaningful work experience. • Excellent programming skills in Python and strong understanding of large language models, transformer architectures, and the training and evaluation of generative models. • Foundational understanding of reinforcement learning algorithms and implementation, including MDPs, policies, and reward design. • Deep understanding of software engineering fundamentals, code generation, automated testing, and program correctness. • Proven track record to lead model development life cycles, including dataset versioning, experiment tracking, and evaluation pipelines. Ways to stand out from the crowd: • Experience training or post-training state-of-the-art coding models or models designed for software engineering agents. • Experience with execution-based rewards, verifiable rewards, reward hacking mitigation, and automated code evaluation. • Familiarity with coding benchmarks and evaluation environments such as SWE-bench, etc. Widely considered to be one of the technology world’s most desirable employers, NVIDIA offers highly competitive salaries and a comprehensive benefits package. As you plan your future, see what we can offer to you and your family www.nvidiabenefits.com/ Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The

View the official posting →