Artificial Intelligence Engineer

TOP IT Service; Ahmedabad District; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

TOP IT Service in Ahmedabad seeks an AI/software engineer with 5+ years of experience to design and implement RAG pipelines for document search and grounded answer generation. You will build ingestion for PDFs, DOCX, spreadsheets and other semi-structured data, and develop parsing, embedding, indexing, and retrieval workflows.

The role requires expertise in vector databases, hybrid retrieval strategies, and LLM tooling such as OpenAI, LangChain, and LlamaIndex to deliver production-ready AI

Qualifications

• 5+ years of AI/software engineering experience.
• Strong hands-on experience with Python.
• Practical experience building RAG systems in production or near-production environments.
• Strong understanding of LLM application architecture.
• Experience with document parsing, chunking, embeddings, vector search, and retrieval pipelines.
• Experience using vector databases or search platforms like pgvector, Pinecone, Weaviate, Qdrant, Elasticsearch, OpenSearch, or Azure AI Search.
• Experience using LLM APIs and AI tooling such as OpenAI, Anthropic, LangChain, LlamaIndex or similar frameworks.

Responsibilities

• Design and build RAG pipelines for document search, evidence retrieval, and grounded answer generation.
• Develop ingestion pipelines for PDFs, DOCX files, spreadsheets, and other semi-structured documents.
• Build parsing, chunking, embedding, indexing, and retrieval workflows.
• Work with vector databases, keyword search, and hybrid retrieval strategies.
• Integrate LLMs for claim extraction, classification, re-ranking, summarization, and answer generation.
• Optimize AI workflows for cost, latency, reliability, and production readiness.
• Experience with at least one vector database or search platform such as pgvector, Pinecone, Weaviate, Qdrant, Elasticsearch, OpenSearch, or Azure AI Search.
• Experience using LLM APIs and AI tooling such as OpenAI, Anthropic, LangChain, LlamaIndex or similar frameworks.

Skills

5+ years AI/Software

Python

RAG systems

LLM architecture

Document parsing

Chunking

Embeddings

Vector search

Retrieval pipelines

Vector databases

OpenAI API

LangChain

LlamaIndex

Tools

OpenAI API

LangChain

LlamaIndex

Weaviate

Elasticsearch

Job description

• 5+ years of AI/software engineering experience.
• Strong hands-on experience with Python.
• Practical experience building RAG systems in production or near-production environments.
• Strong understanding of LLM application architecture.
• Experience with document parsing, chunking, embeddings, vector search, and retrieval pipelines.

Role & responsibilities

• Design and build RAG pipelines for document search, evidence retrieval, and grounded answer generation.
• Develop ingestion pipelines for PDFs, DOCX files, spreadsheets, and other semi-structured documents.
• Build parsing, chunking, embedding, indexing, and retrieval workflows.
• Work with vector databases, keyword search, and hybrid retrieval strategies.
• Integrate LLMs for claim extraction, classification, re-ranking, summarization, and answer generation.
• Optimize AI workflows for cost, latency, reliability, and production readiness.
• Experience with at least one vector database or search platform such as pgvector, Pinecone, Weaviate, Qdrant, Elasticsearch, OpenSearch, or Azure AI Search.
• Experience using LLM APIs and AI tooling such as OpenAI, Anthropic, LangChain, LlamaIndex or similar frameworks.

Location: Ahmedabad