RAG Engineer + AI Developer

Job Title: RAG Engineer + AI Developer

Experience: 4–7 Years

Relevant Hands-on Experience: 1–3 Years in RAG / AI Development

Location: PAN India

Employment Type: Contract / Project-Based

Openings: 3 Positions

Job Summary

We are looking for skilled RAG Engineers / AI Developers with strong hands-on experience in Retrieval-Augmented Generation (RAG), Python, FastAPI, LangChain, LangGraph, LLM integration, vector databases, and AI application development.

The ideal candidate should have practical experience building production-ready RAG applications, integrating enterprise data sources with LLMs, developing document-processing pipelines, and implementing semantic search and vector-based retrieval solutions.

The candidate will work closely with AI/ML, backend, data, and engineering teams to design and deliver scalable Generative AI and RAG solutions for enterprise use cases.

Key Responsibilities

RAG Application Development

- Design, develop, and maintain Retrieval-Augmented Generation (RAG) applications.
- Build RAG pipelines using enterprise documents and structured/unstructured data sources.
- Design document ingestion, parsing, chunking, embedding, indexing, retrieval, and generation workflows.
- Implement semantic search and context retrieval mechanisms.
- Improve retrieval relevance, context quality, and LLM response accuracy.
- Develop production-ready RAG architectures that can scale with enterprise workloads.

Python & API Development
- Develop AI applications and backend services using Python.
- Build scalable APIs using FastAPI.
- Develop RESTful APIs for AI applications and LLM-powered services.
- Integrate AI services with databases, enterprise applications, and external APIs.
- Implement authentication, validation, error handling, logging, and API security.

LangChain & LangGraph
- Develop AI workflows using LangChain and LangGraph.
- Build structured LLM workflows and agentic/RAG pipelines.
- Implement prompt templates, chains, retrievers, tools, and workflow orchestration.
- Design stateful workflows using LangGraph where required.
- Integrate multiple AI components into production-ready applications.

LLM Integration
- Integrate LLM platforms such as:
- OpenAI
- Google Gemini
- Anthropic Claude
- Develop LLM-powered applications based on business requirements.
- Implement prompt engineering and context-management strategies.
- Optimize LLM responses for relevance, accuracy, consistency, and latency.
- Handle LLM API integration,



error handling, rate limits, and production considerations.

Vector Search & Embeddings
- Work with vector databases such as:
- PGVector
- Pinecone
- FAISS
- Implement embedding generation and vector indexing.
- Design semantic and similarity-search solutions.
- Optimize retrieval strategies and ranking.
- Work with metadata filtering and hybrid retrieval where applicable.
- Understand vector search, embeddings, similarity metrics, and retrieval pipelines.

Document Processing
- Build document ingestion and processing pipelines.
- Work with structured and unstructured enterprise data.
- Implement document parsing, text extraction, chunking, metadata extraction, and indexing.
- Handle different document formats and data sources.
- Optimize chunking and retrieval strategies for improved RAG performance.

Production & Integration
- Build scalable and maintainable AI solutions for production environments.
- Integrate RAG applications with databases, APIs, and cloud platforms.
- Troubleshoot application, retrieval, and LLM-related issues.
- Monitor application performance and improve reliability.
- Collaborate with backend, data engineering, ML, and product teams.

Mandatory Technical Skills Programming & Backend
- Python – Mandatory
- FastAPI – Mandatory
- REST APIs
- Backend application development
- API integration

RAG & Generative AI
- Retrieval-Augmented Generation (RAG) – Mandatory
- RAG architecture
- Document ingestion
- Chunking
- Embeddings
- Semantic Search
- Retrieval pipelines
- LLM integration
- Prompt Engineering

AI Frameworks
- LangChain – Mandatory
- LangGraph – Mandatory
- Experience building LLM workflows
- Retrievers, chains, tools, and workflow orchestration

Vector Databases Hands-on experience with at least one of:
- PGVector
- Pinecone
- FAISS

LLM Platforms Hands-on experience integrating one or more:
- OpenAI
- Gemini
- Claude

Database & Development Tools
- PostgreSQL
- SQL
- Git
- Docker

Required Experience
- 4–7 years of total professional experience.
- 1–3 years of relevant hands-on RAG / AI development experience.




- Strong Python development experience.
- Hands-on experience building RAG applications.
- Experience with LangChain and LangGraph.
- Experience implementing vector-search and embedding solutions.
- Experience integrating LLM APIs into applications.
- Experience building APIs using FastAPI.
- Experience working with PostgreSQL and REST APIs.
- Experience with Docker and Git.

Valuable to Have Experience with any of the following will be an advantage:
- Agentic AI
- Multi-agent systems
- Hybrid Search
- Reranking
- RAG evaluation
- RAGAS
- LangSmith
- LLM observability
- Prompt evaluation
- Fine-tuning / LoRA
- Azure OpenAI
- AWS Bedrock
- Google Vertex AI
- Kubernetes
- CI/CD
- Cloud deployment
- AI security and guardrails

Preferred Candidate Profile The ideal candidate should have practical experience moving RAG/GenAI applications beyond proof-of-concept into scalable, production-ready solutions. The candidate should understand the complete RAG lifecycle, including:

Data Ingestion → Document Processing → Chunking → Embeddings → Vector Storage → Retrieval → Context Construction → LLM → Response Generation → Evaluation & Optimization

Strong problem-solving, communication, debugging, and collaboration skills are required.

Interview Process

Round 1: Customer Interview

Round 2: 1–2 Subsequent Client Interview Rounds

Application

Interested candidates can share their updated CV with the following details:

- Total Experience
- RAG / GenAI Experience
- Python Experience
- FastAPI Experience
- LangChain Experience
- LangGraph Experience
- Vector Database Experience
- LLM Experience – OpenAI / Gemini / Claude
- PostgreSQL Experience
- Current Location
- Notice Period / Availability
- Current CTC & Expected CTC

? Email: [email protected] ? WhatsApp: +91 92848 05350

LinkedIn Recruiter Search Keywords

RAG Engineer, RAG Developer, AI Developer, GenAI Developer, Generative AI Engineer, AI Engineer, Machine Learning Engineer, Python Developer, Python AI Developer, Retrieval Augmented Generation, RAG, Generative AI, GenAI, LLM, Large Language Models, LLM Engineer, LangChain, LangGraph, FastAPI, Python, Vector Database, Vector Search, PGVector, Pinecone, FAISS, Embeddings, Semantic Search, Document Processing, OpenAI, GPT, Gemini, Claude, Anthropic, Prompt Engineering, PostgreSQL, REST API, Docker, Git, Agentic AI, AI Agents, RAG Pipeline, RAG Architecture, LLM Integration, Enterprise AI.

📌 RAG Engineer + AI Developer (Pune)
🏢 Philodesign Technologies
📍 Pune