AI/ML: Strong foundation in AI/ML, covering supervised, unsupervised, and reinforcement learning methods, along with probabilistic modeling. Well-versed in NLP and its advanced applications with Large Language Model (LLM).
LLMs and Post-training: In-depth knowledge of LLMs and Transformer-based architectures, and post-training LLMs through supervised fine-tuning (including LoRA and PEFT) and reinforcement learning (PPO, DPO, GRPO).
Conversational AI: Experienced in building conversational systems, including implementing agents with advanced reasoning techniques such as Chain-of-Thought (CoT) and ReAct (Reason+Act).
Text Evaluation: Proficient in developing text evaluation metrics and using LLMs as judges.
Programming Languages: Python (primary), Java, C
Miscellaneous: NumPy, Pandas, PyTorch, Transformers, TRL, SQL, Shell script