Machine Learning Engineer, LLM Post-Training

Responsibilities

• Lead post-training of LLMs across the full pipeline including continuous pre-training, SFT, and reinforcement learning (RLHF, PPO, GRPO, DPO)
• Design, build, and curate data for training stages including instruction datasets, preference pairs, and reward signals
• Partner with business and product stakeholders to convert requirements into training plans
• Run large-scale training on mid-to-large GPU clusters using distributed-training techniques like FSDP
• Build and maintain evaluation and reward/verifier pipelines to measure model quality
• Implement promising post-training research into production-ready code

Requirements

• Hands-on LLM post-training experience (CPT, SFT, and RL)
• Demonstrated practical RL experience (RLHF, PPO, GRPO, or DPO)
• Strong data engineering for ML including sourcing, cleaning, and synthetic data generation
• Proven ability to train LLMs on mid-to-large GPU hardware using distributed training
• Strong PyTorch fundamentals
• Familiarity with Hugging Face TRL/Accelerate, DeepSpeed, FSDP, and vLLM
• Understanding of tokenization, attention, and chat templates

Preferred Qualifications

• Experience designing reward models or rule-based verifiers for RL
• Experience with tool-use or agentic model training
• Publications or open-source contributions in LLM post-training or RL

Benefits

• 100% health, dental, and vision coverage for employees
• Top-tier 401(K) plan with company matching
• Paid time off and paid holidays
• FSA, HSA, and commuter benefits
• Team activity budget

About the Company

NewsBreak is a Content Intelligence platform with over 40 million monthly active users, delivering personalized local news powered by advanced AI and recommendation systems.