AI Engineer

Hello! We are looking for an AI Engineer to build the AI-powered parts of Edverise. Edverise helps businesses find and compare verified technology vendors using verified reviews, delivery history and transparent rankings instead of ad spend. Edverise is AI-native, so the features you build, such as natural language search and vendor matching, sit right at the heart of how buyers use the product.

About the team

You will work with our backend and frontend developers, the people who shape our product, and the folks who look after review quality. You will take AI ideas from a quick prototype to something reliable in production, and we will make time to test and measure properly along the way.

What you will work on

• Build natural language search that turns a buyer's plain-English need into a shortlist of relevant vendors.
• Create retrieval-augmented generation (RAG) pipelines over vendor profiles, verified reviews and delivery history.
• Write and test prompts, and set up evaluations so we know when AI output is accurate and fair.
• Wrap AI features in clean Python APIs with FastAPI that our product can call.
• Keep an eye on the cost, speed and quality of LLM calls, and improve all three over time.
• Add safeguards so AI output stays grounded in verified data and never invents vendor facts.

What we are looking for

• 2-4 years of software engineering experience, including hands-on work building LLM-powered features.
• Strong Python and experience calling LLM APIs in production.
• Practical experience with RAG, embeddings and a vector database.
• Familiarity with frameworks such as LangChain or LlamaIndex.
• A careful, evidence-based approach: you test outputs instead of simply trusting them.

What success looks like

In your first 3 months, you have shipped your first AI feature to real users, set up a basic evaluation process, and you understand our data well.

By 6 months, you own a core AI feature such as search or matching, you can show clear gains in its quality, and you have helped bring cost and speed under control.

How we work

This is a full-time role based at our office on the 11th floor of O-Hub in Infocity, Bhubaneswar. We will walk you through working hours and the team's weekly routine during the interview process.

Day to day you will use GitHub, Python, Docker and the LLM providers we work with. We keep things simple: clear goals, honest feedback, and plenty of room to ask questions and learn. If this sounds like you, we would love to hear from you!