Key Responsibilities :

- Design, develop, fine-tune, and deploy LLM-based solutions using frameworks like Hugging Face, LangChain, or LlamaIndex.

- Develop and maintain prompt templates, few-shot examples, and chain-of-thought logic for LLM applications.

- Build and optimize AI/ML models using PyTorch and related libraries.

- Implement end-to-end AI workflows - from data ingestion and preprocessing to model training, evaluation, and deployment.

- Integrate LLMs and AI models with internal applications and APIs for real-world use cases.

- Collaborate with data, engineering, and product teams to identify and deliver AI use cases.

- Stay updated on the latest trends in Generative AI, LLMs, RAG (Retrieval-Augmented Generation), and multimodal models.

- Optimize models for performance, scalability, and cost efficiency in production environments.

Required Skills & Experience :

- Strong proficiency in Python and AI/ML development.

- Experience working with PyTorch (preferred) or TensorFlow/Keras.

- Expertise in Prompt Engineering - designing structured, context-aware, and optimized prompts for LLM tasks.

- Hands-on experience with LLMs such as OpenAI GPT, Claude, LLaMA, Mistral, or similar.

- Familiarity with LangChain, Hugging Face Transformers, or RAG-based architectures.

- Strong understanding of NLP concepts (tokenization, embeddings, text generation, summarization).

- Knowledge of data preprocessing, feature engineering, and model evaluation techniques.

- Experience with API development and deployment (Flask, FastAPI, or similar).

- Exposure to cloud platforms (AWS, GCP, Azure) and containerization (Docker/Kubernetes).

- Strong analytical, debugging, and problem-solving skills