Skills

AWS/Azure/GCP, Fast API ,Gen AI tools Generative AI (LLMsRAG Fine-tuning)

LangChain / LangGraph / LlamaIndex / CrewAI / AutoGen Python ,Vector Databases (e.g. Pinecone)

Project Highlights

You will work on cutting-edge AI solutions focused on Generative AI, Retrieval- Augmented Generation (RAG), and Agentic AI.

The role involves building intelligent applications using Large Language Models (LLMs), knowledge graphs, and up-to-date AI frameworks to deliver scalable, production-ready solutions for enterprise use cases.

Roles and Responsibilities

Design, develop, and deploy Generative AI applications using Large Language Models (LLMs) such as GPT, Claude, Llama, and Gemini.

Build end-to-end Retrieval-Augmented Generation (RAG) pipelines using vector databases, embeddings, hybrid search, and re-ranking techniques.

Develop Agentic AI solutions using frameworks like LangChain, LangGraph ,CrewAI, AutoGen, or LlamaIndex.

Integrate Knowledge Graphs (Neo4j/GraphRAG) with AI applications to improve contextual reasoning and response accuracy.

Develop and optimize REST APIs and backend services using Python and FastAPI.

Deploy AI solutions on AWS, Azure, or GCP using Docker and CI/CD pipelines,ensuring scalability and reliability.

Implement Responsible AI practices, including guardrails for hallucination, prompt injection,



bias mitigation, and data security.

Collaborate with cross-functional teams to gather requirements, design AI solutions, troubleshoot issues, and deliver production-ready applications.

Requirements

- 4–6 years of overall software development or AI/ML engineering experience with hands-on Generative AI project exposure.
- Strong proficiency in Python and frameworks such as FastAPI, PyTorch, or TensorFlow.
- Experience building Generative AI applications using LLMs (GPT, Claude, Llama, Gemini, Mistral, etc.).
- Hands-on experience with RAG pipelines, embeddings, vector databases (Pinecone, Chroma, FAISS, Weaviate, Milvus, pgvector), and prompt engineering.
- Experience with Agentic AI frameworks such as LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or LlamaIndex.
- Practical knowledge of Neo4j, Graph Databases, GraphRAG, and Cypher queries.
- Experience with cloud platforms (AWS, Azure, or GCP), Docker, Git, and CI/CD pipelines.
- Familiarity with SQL/NoSQL databases, ETL processes, and REST APIs.
- Strong analytical, debugging, and problem-solving skills with excellent communication abilities.

Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related field.

📌 Artificial Intelligence Engineer (Bengaluru)
🏢 Vastika
📍 Bengaluru