We are seeking an experienced Agentic AI / Generative AI Engineer to design, develop, and deploy intelligent AI solutions powered by Large Language Models (LLMs), AI Agents, Retrieval-Augmented Generation (RAG), and modern AI frameworks. The ideal candidate should have hands-on experience building AI copilots, autonomous agents, conversational AI solutions, and enterprise-grade GenAI applications.
Key Responsibilities
- Design and develop Agentic AI applications leveraging LLMs such as GPT, Claude, Gemini, Llama, and Mistral.
- Build AI Agents capable of reasoning, planning, tool usage, and autonomous task execution.
- Develop RAG-based solutions using vector databases and enterprise knowledge repositories.
- Implement prompt engineering, fine-tuning, and optimization techniques to improve model performance.
- Integrate AI applications with APIs, databases, enterprise systems, and cloud services.
- Build multi-agent workflows using frameworks such as CrewAI, LangGraph, AutoGen, Semantic Kernel, and LangChain.
- Develop conversational AI, virtual assistants, copilots, and knowledge management solutions.
- Monitor AI applications for accuracy, scalability, security, and governance requirements.
- Collaborate with business stakeholders to identify AI use cases and translate them into technical solutions.
Must-Have Skills (Screening)
- Python Development
- LLMs (GPT, Claude, Gemini, Llama)
- Agentic AI Frameworks (LangGraph/CrewAI/AutoGen)
- RAG Implementation
- Vector Databases
- Prompt Engineering
- API Integrations
- Cloud (Azure OpenAI/AWS Bedrock) ANY
- Production Deployment Experience
- GenAI Application Development
Generative AI
- OpenAI GPT, Azure OpenAI, Gemini, Claude, Llama
- Prompt Engineering
Agentic AI
- AI Agents
- Multi-Agent Systems
- LangChain
- LangGraph
Programming
- Python (Mandatory)
- FastAPI / Flask