Description

Build and maintain production-grade Generative AI solutions, focusing on RAG architectures, prompt engineering, and agent frameworks.

This role is on-site.

Responsibilities

• Design and implement end-to-end Generative AI applications using RAG, embedding, and fine-tuning techniques.
• Develop agent-based systems using frameworks like LangChain, LangGraph, and Google ADK.
• Integrate structured and unstructured data sources to build scalable RAG pipelines.
• Deploy and manage AI services on cloud platforms, primarily Azure AI and GCP Vertex AI.
• Write clean, testable Python code for APIs and backend services using Flask or FastAPI.

Required Skills

• 6+ years of software engineering experience with a strong focus on Python.
• 2+ years of hands-on experience with Generative AI and LLM integration.
• Proficiency with Azure AI services and Python programming.
• Experience with agent frameworks such as LangChain, LangGraph, or CrewAI.
• Understanding of RAG methodologies, prompt engineering, and vector search.
• Solid grasp of API integration, test automation, and software engineering principles.
• Experience with TensorFlow, NLP, and deep learning concepts.

Preferred Skills

• Hands-on experience with GCP services including Vertex AI, Gemini, and Cloud Run.
• Familiarity with AWS Bedrock and multi-cloud AI deployments.

Key Skills

Education

Any Graduate