Ml Engineer

1. Strong understanding of Reinforcement Learning (RL) and algorithms like PPO, Reward Trainer.

2. Deep Understanding of Python and has deep ability to write algorithms and code.

3. Experience in training and optimizing Machine Learning and Deep Learning models.

4. Proficiency in training and fine-tuning large language models (e.g., LLAMA, GPT, BERT).

5. Expertise in Python frameworks like TensorFlow, PyTorch.

6. Knowledge of Natural Language Processing (NLP) techniques and transformer architectures. 7. Familiarity with model quantization and optimization techniques.

8. Experience with data annotation, feedback collection, and creating preference-based datasets. 9. Ability to work with tools for distributed training and deployment (e.g., Hugging Face, Ray, or similar).

10. Mathematical foundation in linear algebra, statistics, and probability (Preferred).

11. Understanding of evaluation metrics for RLHF processes and user-aligned AI systems (Preferred).