Empedance Consultancy Services
Website:
empedance.com
Job details:
RAG / Generative AI Engineer
Company: Empedance Consultancy Services Pvt Ltd
Job Type: Full-time
Experience: 3–4 years
Seniority Level: Mid-Senior level
Workplace Type: Remote
Location: Bengaluru, Karnataka, India
🚨 Immediate Joiner Required
We are looking for a RAG / Generative AI Engineer with 3–4 years of overall IT/software development experience, including 1–2 years of hands-on experience building RAG applications.
Immediate joiners are strongly required for this position.
About the Role
The ideal candidate should have practical experience developing LLM-powered applications and a strong understanding of the complete Retrieval-Augmented Generation (RAG) pipeline, including document ingestion, preprocessing, chunking, embeddings, vector search, retrieval, reranking, prompt construction, LLM generation, evaluation, and deployment.
This is a hands-on engineering role focused on developing and optimizing production-ready AI/RAG applications.
Key Responsibilities
- Design and develop end-to-end RAG pipelines.
- Build document ingestion and processing pipelines for PDFs, documents, web content, and other data sources.
- Implement document chunking, metadata extraction, embedding generation, and indexing.
- Develop semantic and hybrid search using vector databases.
- Implement retrieval optimization techniques such as metadata filtering, query transformation, and reranking.
- Integrate LLMs, embedding models, and AI APIs.
- Develop RAG applications using LangChain / LangGraph.
- Evaluate and improve retrieval accuracy, response quality, latency, and cost.
- Reduce hallucinations and improve contextual relevance.
- Develop APIs and backend services for AI applications.
- Deploy and maintain AI/RAG applications in production.
Required Qualifications
- 3–4 years of overall experience in IT/software development.
- 1–2 years of hands-on experience in RAG / Generative AI.
- Immediate joiner required.
- Strong proficiency in Python.
- Hands-on experience with LangChain.
- Strong understanding of RAG architecture and LLM application development.
- Experience with vector databases such as Qdrant, ChromaDB, Pinecone, Weaviate, or equivalent.
- Good understanding of embeddings, semantic search, vector search, and similarity search.
- Experience with document processing, chunking, indexing, and retrieval pipelines.
- Experience with LLM APIs and prompt engineering.
- Experience developing REST APIs and backend services.
- Good understanding of Git, testing, debugging, and software development practices.
Good to Have
- Experience with hybrid search and reranking.
- Experience with RAG evaluation and benchmarking.
- Experience optimizing retrieval quality, latency, and token usage.
- Experience with FastAPI.
- Experience with Docker and cloud deployment.
- Experience with OpenAI, Anthropic, Gemini, Hugging Face, or similar platforms.
- Experience building production-grade GenAI applications.
Candidate Profile
We are specifically looking for candidates who have built and worked on real-world RAG systems, rather than candidates whose experience is limited to basic LLM API integration or chatbot development.
Candidates should be comfortable discussing practical RAG challenges including:
- Chunking strategies
- Embedding selection
- Vector database optimization
- Retrieval quality
- Hybrid search
- Reranking
- Context window management
- Hallucination reduction
- RAG evaluation
- Production scalability and latency
Click on Apply to know more.