Research Engineer / Scientist, Agentic RL Post-Training (all genders)

Summary

Permanent, full-time role at ellamind, Software Development team. RoleRadar classifies it as research. Listed locations: Bremen; Berlin. Skills mentioned include PyTorch, vLLM / TensorRT, LLMs, RLHF & post-training, Fine-tuning and Reinforcement learning.

Generated by RoleRadar from facts in the posting. We don't reproduce the job description; read it in full on ellamind's job page.

Key facts

Salary

Not published by the employer

Location

• Bremen
• Berlin

Workplace

Not stated in the posting

Countries

Germany

Inferred by RoleRadar from the listed locations.

Experience

Not stated in the posting

PhD

Not mentioned

Visa sponsorship

Not stated in the posting

Team

Software Development

Skills mentioned

• PyTorch
• vLLM / TensorRT
• LLMs
• RLHF & post-training
• Fine-tuning
• Reinforcement learning
• Distributed training
• Inference optimization