AI Architect- Agentic AI & RAG

Job Overview:
We are looking for an experienced AI Architect to lead solution design and development efforts in the areas of

Agentic AI

and

Retrieval-Augmented Generation (RAG) .

The ideal candidate will have strong experience working with large language models (LLMs), building intelligent applications using frameworks like LangChain or LlamaIndex, and designing scalable AI pipelines.

Key Responsibilities:
Design and implement

RAG-based systems

combining LLMs with vector databases and internal document sources.
Build

task-based AI agents

(e.g., chatbots, assistants) that can perform multi-step operations and integrate with external tools or APIs.
Develop and maintain

prompt templates , embedding pipelines, and orchestrators using frameworks like

LangChain, LlamaIndex , etc.
Work with

data and ML teams

to connect AI applications with enterprise knowledge sources (SharePoint, Confluence, databases, etc.).
Evaluate and integrate

embedding models ,

vector databases

(FAISS, Pinecone, Chroma), and

LLM APIs

(OpenAI, Azure OpenAI, etc.).
Collaborate with cross-functional teams to identify use cases, define architecture, and deliver PoCs or MVPs.
Contribute to CoE documentation, reusable components, and architecture patterns for RAG and agent-based solutions.

Required Skills:
5 years of hands-on experience in

Python

with exposure to building AI/NLP applications.
Practical experience with

LLM tools like LangChain, LlamaIndex , or equivalent.
Experience building

RAG systems

using vector stores and document loaders.
Familiarity with

LLM APIs

such as OpenAI, Cohere, or HuggingFace models.
Understanding of

prompt design ,

embedding models

(e.g., OpenAI, BGE, SentenceTransformers).
Working knowledge of

REST APIs ,

JSON , and integrating AI agents with backend systems.