Job Title : AI Engineer (Generative AI & Data Products)

Locations : Gurgaon (Delhi NCR) or Bangalore (On-site)

About the Role :

We are seeking an experienced, product-minded AI Engineer specializing in Generative AI and Agentic systems to design and build production-grade Data Products. In this role, you will bridge the gap between core backend software engineering and cutting-edge artificial intelligence, transforming complex enterprise data into intelligent, autonomous applications.

The ideal candidate has a strong foundation in data structures, a proven track record of shipping real-world digital products, and hands-on experience building multi-agent workflows and advanced retrieval systems that solve specific, high-impact business use cases.

Key Responsibilities :

- Build GenAI Data Products : Architect and deploy end-to-end data products that leverage Large Language Models (LLMs) to automate complex workflows, extract insights, and process large-scale data structures.

- Design Agentic Workflows : Implement autonomous, multi-agent systems capable of sequential reasoning, tool-calling, and independent decision-making for specific business use cases.

- Advanced Data Ingestion : Design and optimize Retrieval-Augmented Generation (RAG) pipelines, custom data indexers, and vector database management systems to handle structured and unstructured data.

- Production Engineering : Write clean, production-grade backend APIs and maintain high availability, security standards, and low latency for deployed AI features.

Required Skills & Qualifications :

- Experience : 6+ years of software engineering experience, with a heavy focus on building and deploying production-scale ML/GenAI systems.

- GenAI & Agentic Expertise : Hands-on experience with LLM orchestration frameworks (e.g., LangChain, LangGraph, CrewAI) and building practical agent tools.

- Data Product Mindset : Proven experience translating raw data and complex business rules into user-facing AI applications (e.g., intelligent search, automated compliance, insight generation).

- Core Tech Stack : Strong proficiency in Python, FastAPI/Flask, SQL, and Vector Databases (e.g., FAISS, Redis, Pinecone).

- Cloud Infrastructure : Experience deploying applications on cloud platforms (AWS, GCP, or Azure).