Staff AI Engineer Model Post-Training and Alignment

Design, execute, and optimize post-training pipelines for large language models across data strategy, reward modeling, reinforcement learning, alignment, evaluation, and production inference.

Responsibilities

• Lead and execute LLM post-training pipelines
• Design DPO and GRPO training paradigms
• Develop domain-specific data recipes and augmentation pipelines
• Train specialized small models from scratch
• Build and refine reward models
• Design and implement RLAIF closed-loop systems
• Optimize inference efficiency and deploy models
• Evaluate model performance with benchmarks and feedback loops
• Collaborate to productionize training and deployment workflows

Requirements

• Bachelor's degree in Computer Science, AI, Machine Learning, or a related field
• 8+ years of industry experience
• Strong experience with large model post-training
• Preference learning and alignment techniques including DPO and GRPO
• Reinforcement learning fundamentals
• Domain-specific data strategies
• Training specialized small models from scratch
• Reward modeling and RLAIF
• Low-latency production deployment using vLLM, SGLang, or similar

Benefits

• L&D programs
• Education subsidy
• Team building programs
• Company events
• Wellness allowances
• Meal allowances
• Comprehensive healthcare schemes for employees and dependants
• Competitive total compensation package