Senior Architect, Model Performance and Post-Training
Core
Drive performance modeling, evaluation, and post-training of large language models specialized in code generation and software engineering tasks.
Role type
Senior IC machine-learning engineer (model performance & post-training)
Builds
Production-ready coding models and evaluation pipelines
Domain
AI / Software Engineering / Large Language Models
Deliverable
production ML models
Required skills
Python, large language models, transformer architectures, reinforcement learning, software engineering fundamentals, code generation, automated testing, experiment tracking, dataset versioning
Preferred skills
state-of-the-art coding model training, execution-based rewards, verifiable rewards, reward hacking mitigation, automated code evaluation, SWE-bench
Technologies
Python, SFT, RL, reward modeling
Responsibilities
Develop frameworks to measure and analyze coding model performance; Develop and optimize post-training pipelines (SFT, RL, reward modeling); Analyze benchmark results and training dynamics to identify improvement opportunities; Build scalable infrastructure for training experiments and evaluation pipelines
Seniority
Senior, hands-on IC
