LLM Engineer(Reinforcement Learning)

We are looking for the best LLM Engineer(Reinforcement Learning) LLM.

Responsibilities

• LLM
• PLM Fine-tuned LLM Direct Alignment Algorithm / PPO, GRPO, DPO
• Reward Hacking, Self-Refine
• API
• Tool LLM

Qualifications

• Deep Learning NLP 3
• Python & pytorch
• PyTorch
• GPU LLM Trouble shooting
• Slurm, DDP, Horovod

Preferred Qualifications

• Deep Learning/NLP (ACL, EMNLP, NeurIPS)
• Docker Kubernetes
• GPU
• GPU Training Inference
• LLM Post-training
• Supervised Fine-Tuning Parameter Efficient Fine-Tuning

Interview Process

• - - (1) - (3) -
• ,.
• .

Additional Information

• ,,,,,,.
• 30MB PDF. (URL recruit@42dot.ai.)
• .
• .
• .
• 42dot,.
• 3.

※.

• 42dot, 42dot Way →
• 42dot, Employee Engagement Program →