Research Engineer (Agentic Models)

📋 Description Design, implement, and maintain SFT/RL post-training pipelines for agents. Train and adapt LLMs for agent workflows, including planning. Build evaluation/simulation environments for agents to act and be measured. Design evaluation metrics for agent behavior; analyze traces for improvements. Analyze training results to improve model architectures, training recipes, and datasets. Work with distributed GPU clusters and MapReduce-style data processing. 🎯 Requirements Hands-on experience training LLMs (pre-, fine-, or post-training). Deep expertise in PyTorch and specialized LLM stacks (Megatron, NeMo, etc.). LLM fundamentals: architectures, tokenization, data pipelines, batching. Ability to own projects end to end from problem to iteration. Product-aware mindset: translate product needs into modeling and evaluation. 3+ years of Python experience in modern ML codebases.