- Design, develop, and deploy AI-powered applications using Large Language Models (LLMs)
- Build and optimize RAG (Retrieval-Augmented Generation) pipelines
- Develop Agentic AI systems using frameworks like LangGraph
- Implement and maintain machine learning models for various business use cases
- Work with Python and/or R for data processing, model building, and experimentation
- Integrate AI models with APIs, databases, and external systems
- Fine-tune LLMs and optimize prompt engineering strategies
- Ensure scalability, performance, and reliability of AI systems
- Strong experience in Python (mandatory) and working knowledge of R
- Hands-on experience with Machine Learning algorithms and frameworks
- Practical knowledge of LLMs (e.g., GPT, open-source models)
- Experience building RAG pipelines using vector databases (e.g., FAISS, Pinecone)
- Familiarity with LangGraph / LangChain / Agentic AI frameworks
- Solid understanding of Artificial Intelligence concepts and NLP
- Experience with APIs, microservices, and cloud platforms (AWS/Azure/GCP is a plus)
- Strong problem-solving and analytical skills
- Experience in prompt engineering and LLM fine-tuning
- Knowledge of embeddings, semantic search, and vector databases
- Exposure to MLOps tools and deployment pipelines
- Experience working in agile environments
