Generative AI Architect - Python/LLM

Description:

Role Overview :

We are looking for a GenAI Engineer with hands-on experience in building LLM-powered applications, especially Retrieval-Augmented Generation (RAG) systems. The ideal candidate should be comfortable working with structured and unstructured data, embeddings, vector databases, and deploying GenAI solutions in real-world environments.

Key Responsibilities :

- Design and build RAG-based GenAI applications

- Work with structured (DBs, tables) and unstructured data (PDFs, docs, text)

- Implement document ingestion, chunking, embedding generation, and retrieval

- Integrate LLMs (OpenAI, Azure OpenAI, open-source models like LLaMA/Mistral)

- Use vector databases for similarity search and retrieval

- Optimize prompts, context size, and response quality

- Build APIs/services to expose GenAI functionality

- Collaborate with backend, data, and DevOps teams

- Handle evaluation, logging, and basic monitoring of GenAI outputs

Required Skills (Must Have) :

- Strong understanding of LLMs and GenAI fundamentals

- Hands-on experience with RAG architecture

- Experience handling :

1. Structured data (SQL / NoSQL)

2. Unstructured data (PDFs, text, documents)

3. Embeddings and similarity search concepts

Vector databases (any one) :

i. FAISS

ii. ChromaDB

iii. Pinecone

iv. Weaviate

- Python for GenAI pipelines

- Prompt engineering basics

- API integration experience

Good to Have (Bonus) :

- Knowledge of LangChain / LlamaIndex

- Experience with knowledge graphs (Neo4j, graph-based RAG)

- Model hosting / inference optimization

- Experience deploying GenAI apps on AWS / Azure / GCP

- Understanding of security, PII masking, or data governance in GenAI

- Basic MLOps exposure (logging, evaluation, versioning)