Senior Applied Scientist (Post-Training)

What you'll do

• Build and run end-to-end LLM post-training pipelines and train reward models on GPU infrastructure.
• Develop on-policy and online evaluation using LLM-as-a-Judge, and turn evaluation rubrics into production reward functions.
• Drive complex work across teams, provide technical leadership, and mentor scientists and machine-learning engineers.

What they ask for

• Hands-on experience with LLM post-training and RL fine-tuning, including SFT, DPO, and RFT/GRPO, with end-to-end GPU training runs.
• Experience developing reward models; research-level experience is sufficient.
• Strong knowledge of generative AI, foundation models, transformers, reinforcement learning, and preference learning.
• Strong programming skills, especially Python, and experience with PyTorch or TensorFlow.

Nice to have

• Experience evaluating agentic AI, including multi-turn trace analysis and LLM-as-a-Judge.
• Published work in post-training, RLHF/RLAIF, preference learning, or reward modeling; or experience with GPU training platforms such as Databricks or Fireworks.

Pay

USD 164,400.00 - USD 262,600.00 annually (base salary); USD 156,200.00 - USD 249,400.00 annually (base salary)

Tools

SFT, DPO, RFT/GRPO, GPU infrastructure, LLM-as-a-Judge, Python, PyTorch, TensorFlow

AI focus

LLM post-training, reinforcement fine-tuning, reward modeling, and evaluation of agentic AI.