AI Engineer (Generative AI & RAG)

Job Description:

Responsibilities

• Design, develop, and maintain RAG-based chatbot systems and AI agents.
• Integrate Large Language Models (OpenAI, Claude, open-source LLMs) into production applications.
• Build and manage vector databases (Pinecone, Weaviate, Milvus, etc.) for semantic search and retrieval.
• Develop robust document ingestion, chunking, embedding, and retrieval pipelines.
• Optimize prompt engineering strategies and overall model performance.
• Improve response accuracy, latency, and reliability of AI systems through continuous evaluation.
• Deploy and monitor AI services in production environments using Docker and Cloud platforms.
• Collaborate with product and leadership teams to translate complex business needs into technical AI solutions.
• Maintain and iterate upon existing chatbot architectures to ensure scalability.

Qualification & Experience

• Bachelor's or Master's degree in Computer Science, Information Technology, or a related technical field.
• Relevant certifications in AI/ML or Cloud Computing will be an added advantage.
• Core Skills: Strong proficiency in Python and experience with RAG architecture & pipelines.
• AI Expertise: Deep understanding of Embeddings, chunking strategies, and Prompt Engineering.
• System Design: Ability to design scalable RAG systems and manage cost/token optimization.
• Backend: Experience with FastAPI or Flask for REST API development.
• DevOps: Basic knowledge of Docker, CI/CD, and Cloud infrastructure (AWS/GCP/Azure).
• Data: Familiarity with SQL/NoSQL databases and data preprocessing techniques.
• Nice to Have: Experience with LangChain or LlamaIndex, fine-tuning basics, and AI security awareness.
• 2 Years (Generative AI & RAG),