Job description :

We are looking for a hands-on Gen AI Engineer with a strong Python and Data Engineering background, who has real-world experience building, deploying, and scaling Generative AI solutions.

This role requires practical exposure-not theoretical knowledge or certification-only experience.

Experience Range : 8 - 15 years

Key Responsibilities :

- Design, build, and deploy production-grade Gen AI solutions

- Develop and optimize RAG (Retrieval-Augmented Generation) pipelines

- Build and manage Agentic AI workflows for autonomous task execution

- Integrate LLMs (LLaMA, OpenAI, Claude, etc.) into business applications

- Work with vector databases for embedding storage and retrieval

- Handle real-time inference pipelines and low-latency AI services

- Collaborate with data engineers, backend teams, and product stakeholders

- Ensure scalability, monitoring, and performance optimization of Gen AI systems

Must-Have Skills :

- Strong Python (production-level coding experience)

- Data Engineering background (ETL / ELT, pipelines, APIs, data processing)

- Hands-on Gen AI experience in real projects (not POCs alone)

- RAG architectures - end-to-end implementation

- Agentic AI frameworks (LangGraph, AutoGen, CrewAI or similar)

- LLMs : LLaMA (preferred), OpenAI, Hugging Face models

- Vector Databases : FAISS, Pinecone, Weaviate, Milvus, Chroma

- Prompt engineering with versioning and evaluation

- API development (FastAPI / Flask)

Good to Have :

- MLOps exposure (Docker, CI / CD, model deployment)

- Experience with real-time streaming or async systems

- Cloud exposure : AWS / Azure / GCP

- Experience optimizing latency, token cost, and throughput

What We Do NOT Want :

- Purely theoretical Gen AI knowledge

- Certification-only profiles without real project implementation

- Fresh Gen AI learners without backend or data engineering foundation