Job Summary
We are seeking a passionate and skilled Generative AI Engineer with 3+ years of experience in building LLM-based applications. The ideal candidate should have hands-on experience with multi-agent frameworks (LangGraph, CrewAI), agent orchestration, RAG pipelines, and Chain of Thought (CoT) reasoning to develop intelligent, context-aware systems.
Key Responsibilities
- Design and develop multi-agent LLM applications using frameworks like LangGraph and CrewAI.
- Build, configure, and orchestrate intelligent agents and tools for autonomous task execution.
- Implement RAG (Retrieval-Augmented Generation) and Agentic RAG pipelines to augment LLMs with external data sources.
- Develop and fine-tune prompts to support Chain of Thought and step-wise reasoning.
- Integrate vector databases (e.g., FAISS, Pinecone, Chroma) for context retrieval.
- Collaborate with frontend/backend teams to embed GenAI capabilities into products.
Required Skills
- Strong programming experience with Python.
- Hands-on with LangGraph, CrewAI, LangChain, or other agent frameworks.
- Solid understanding of LLMs, prompt engineering, and tool invocation patterns.
- Experience with RAG, vector databases, embeddings, and document chunking.
- Knowledge of Chain of Thought prompting, memory handling, and agent planning logic.
- Familiarity with OpenAI, Hugging Face, or other LLM APIs.
Nice to Have
- Experience deploying GenAI apps with FastAPI, Streamlit, or React.js.
- Understanding of semantic search, knowledge graphs, or graph databases.
- Exposure to MLOps, Docker, CI/CD pipelines, and cloud deployment (AWS/GCP/Azure).
- Awareness of ethical AI and data governance practices.
