hybrid
AI Engineer - RAG & LLM
AI Engineer - RAG & LLM
CG-VAK Software & Exports Ltd. is seeking a hands-on AI Engineer with expertise in the LangChain ecosystem to design, orchestrate, and optimize intelligent AI workflows. The role involves building an AI-powered Artwork Validation Platform using LLMs and Retrieval-Augmented Generation (RAG) to validate product packaging against global regulatory rules. Key responsibilities include designing RAG pipelines, extracting structured data using LLMs, developing AI workflows with LangChain, and implementing semantic search and embeddings.
About the role
Role & Responsibilities
We are building an AI-powered Artwork Validation Platform that reads global regulatory rules and validates product packaging using LLMs and Retrieval-Augmented Generation (RAG). We are looking for a hands-on AI Engineer with strong expertise in the LangChain ecosystem to design, orchestrate, and optimize intelligent AI workflows.
Key Responsibilities
- Design and build RAG pipelines for rule-based validation
- Extract structured rules from PDF/XML/web sources using LLMs
- Develop AI workflows using LangChain and LangGraph
- Implement semantic search and embeddings for accurate retrieval
- Use LangSmith for debugging, tracing, and evaluation
- Prototype workflows using LangFlow
- Generate explainable AI outputs for artwork validation
- Optimize prompts and reduce hallucinations
Ideal Candidate
- Strong AI Engineer / LLM Engineer profile with hands-on experience building RAG or LLM applications
- Mandatory (Experience): Must have 3+ years of software engineering experience with atleast 6+ months in AI/ML, NLP, or deploying LLM based application
- Mandatory (LLM & RAG): Must have strong hands-on experience building RAG pipelines, LLM workflows, semantic search, or AI-powered retrieval systems
- Mandatory (LangChain Ecosystem): Must have hands-on experience with LangChain. Experience with LangGraph, LangSmith, and LangFlow is highly important
- Mandatory (Vector DB & Embeddings): Must have worked on embeddings and vector databases like Pinecone, FAISS, Weaviate, ChromaDB, etc.
- Mandatory (Programming): Strong Python skills with experience building AI/NLP pipelines or backend AI workflows
- Mandatory (Data Processing): Must have experience working with unstructured data such as PDFs, HTML, XML, scanned documents, or web data
- Mandatory (Prompt Engineering): Must have good understanding of prompt engineering, hallucination reduction, retrieval accuracy, and LLM evaluation
- Mandatory (Company): Service or product companies acceptable given they have real AI/ML, LLM based experience
- Mandatory (Note): Must be comfortable with a 6-day (3 days in office) hybrid work model. Mon-Friday 8:30-5:30 pm and Saturdays 8:30-1:00 pm
- Preferred (Experience): Exposure to food compliance domain