Initiativbewerbung - KI-Forschung & Modellentwicklung (m/w/d)
Core
Research and engineering role focused on training and evaluating Large Language Models (LLMs), specifically using Reinforcement Learning and building evaluation benchmarks.
Role type
Senior IC Machine Learning Researcher (LLM Training & Evaluation)
Builds
Proprietary LLMs, RL environments, and evaluation benchmarks
Domain
Artificial Intelligence / Large Language Models
Deliverable
production ML models
Required skills
LLM training, Reinforcement Learning, RL environment development, benchmark creation, experimental design, training infrastructure
Preferred skills
Distributed training, sandboxed code execution, Open-Source contributions
Technologies
LLMs, Reinforcement Learning, RL environments
Responsibilities
Train and post-train LLMs with Reinforcement Learning, develop RL environments for agent tasks, build benchmarks and evaluations, design clean experiments, build efficient training and evaluation infrastructure
Seniority
Senior, hands-on IC
