JOBSEARCHER

Senior Architect, Model Performance and Post-Training

NVIDIADayton, OHL6 LeadOctober 26th, 2026
Overview: In this role you drive performance modeling, evaluation, and post-training for large language models specialized in code generation and software engineering. You will operate at the intersection of model training, inference optimization, and empirical analysis to boost coding capabilities, efficiency, and developer productivity. You'll design experiments, identify bottlenecks, and translate insights into production-ready features in collaboration with research, infrastructure, and product teams. This is an opportunity to shape state-of-the-art coding models at an industry-leading AI computing company. Compensation / Benefitsequity participationcompetitive salarycomprehensive benefits packageremote work optionsrelevant relocation support (if applicable)career growth opportunities
Responsibilities:
  • Develop frameworks to measure and analyze coding model performance across code generation, debugging, code completion, repository-level reasoning, and multi-step software tasks
  • Develop and optimize post-training pipelines for coding models, including SFT, preference optimization, RL, and reward-based modeling
  • Analyze benchmark results, training dynamics, failure modes, and model behaviors to identify improvements
  • Improve model performance on complex coding tasks via targeted training interventions, reward design, curriculum development, and error analysis
  • Build scalable, reproducible infrastructure for training experiments, evaluation pipelines, and performance analysis
Key requirements:
  • Bachelor's degree (or equivalent) in Computer Science or AI with 12+ years of meaningful work experience
  • Excellent Python programming skills
  • Strong understanding of large language models, transformer architectures, and generative model training/evaluation
  • Foundational knowledge of reinforcement learning algorithms, including MDPs, policies, and reward design
  • Deep understanding of software engineering fundamentals, code generation, automated testing, and program correctness
  • Proven track record leading model development life cycles, including dataset versioning, experiment tracking, and evaluation pipelinescollaboration with cross-functional teamsdata-driven decision makingstrong communication and leadership abilities
  • Python programminglarge language models and transformer architecturestraining/evaluation of generative models