Senior Architect, Model Performance and Post-Training
$224k - $431k • Remote • US, CA, Santa Clara
Posted 6d ago
Job Location
US, CA, Santa Clara
Tech Stack
Remote Work Policy
Fully remote
Categories
LLM Engineer
About the job
NVIDIA is seeking a Senior Engineer to lead the performance modeling, evaluation, and post-training of large language models focused on code generation and agentic coding tasks. This role involves optimizing model capabilities, efficiency, and reliability by working at the intersection of model training, inference, and empirical analysis. You will design experiments to understand model behavior, identify performance bottlenecks, and develop post-training strategies to achieve measurable improvements in coding benchmarks and real-world software engineering tasks. Collaboration with research scientists, infrastructure engineers, and product teams will be key to translating model insights into production-ready features.
Responsibilities
- Develop frameworks for measuring and analyzing coding model performance across various software engineering tasks.
- Develop and optimize post-training pipelines, including SFT, preference optimization, RL, and reward modeling.
- Analyze benchmark results, training dynamics, and model behaviors to identify improvement opportunities.
- Enhance model performance on coding tasks through targeted training, reward design, and error analysis.
- Build scalable infrastructure for training experiments, evaluation pipelines, and performance analysis.
Requirements
- Bachelor's degree in Computer Science or AI, or equivalent experience, with 12+ years of relevant work experience.
- Excellent Python programming skills.
- Strong understanding of large language models, transformer architectures, and generative model training/evaluation.
- Foundational understanding of reinforcement learning algorithms and implementation.
- Deep understanding of software engineering fundamentals, code generation, and automated testing.
- Proven ability to lead model development lifecycles, including dataset versioning, experiment tracking, and evaluation pipelines.
Benefits
- Highly competitive salaries
- Comprehensive benefits package
- Eligibility for equity
- Eligibility for benefits