Machine Learning Engineer, LLM Post-Training
Core
Drive post-training of large language models with a focus on reinforcement learning, data preparation, and evaluation pipelines.
Role type
Senior hands-on Machine Learning Engineer (LLM Post-Training)
Builds
Production-ready LLMs via continuous pre-training, supervised fine-tuning, and reinforcement learning.
Domain
Artificial Intelligence / Large Language Models / Reinforcement Learning
Deliverable
production ML models
Required skills
LLM post-training (CPT, SFT, RL), Reinforcement Learning (RLHF, PPO, GRPO, DPO), Data engineering for ML, Large-scale GPU training, Distributed training (FSDP, tensor/pipeline parallelism), PyTorch, Hugging Face TRL/Accelerate, DeepSpeed, vLLM, Tokenization, Chat templates
Preferred skills
Reward model design, Tool-use / agentic model training, Publications or open-source contributions in LLM post-training
Technologies
PyTorch, Hugging Face TRL, Accelerate, DeepSpeed, FSDP, vLLM
Responsibilities
Lead post-training of LLMs across the full pipeline (CPT, SFT, RL); Design, build, and curate training data (instruction/SFT datasets, preference pairs, reward signals); Partner with product teams to translate use cases into training plans; Run large-scale training on GPU clusters; Build and maintain evaluation and reward/verifier pipelines; Stay current with post-training research.
Seniority
Senior, hands-on IC