Generative AI Engineer

Hi! We are hiring a Generative AI Engineer to design and build the generative features of the Edverise marketplace. Edverise helps businesses find and compare verified technology vendors using verified reviews, delivery history and transparent rankings instead of ad spend. You will own features that write, summarise and explain, such as clear summaries of verified reviews and side-by-side vendor comparisons, and you will make sure every word is grounded in real data.

About the team

You will work closely with our AI and backend engineers, designers and the folks who look after review quality and trust. We test ideas quickly, measure results honestly, and treat accuracy as a feature rather than an afterthought.

What you will work on

• Build LLM features that summarise verified reviews and explain how vendors compare on delivery and quality.
• Design RAG and agent workflows using tools such as LangChain or LlamaIndex.
• Experiment with prompt design, structured outputs and, where it makes sense, fine-tuning open models.
• Build evaluation sets and automated checks for accuracy, tone and hallucinations.
• Work with designers so AI output is easy to read and clearly labelled for users.
• Track model costs and response times, and pick the right model for each job.

What we are looking for

• 2-5 years of software or ML engineering experience, including real work with generative AI.
• Strong Python and hands-on experience with LLM APIs and open models from Hugging Face.
• Experience building RAG systems with embeddings and a vector database.
• A good understanding of evaluation methods for generative output.
• Clear thinking about responsible AI, including bias, accuracy and transparency.

What success looks like

In your first 3 months, you have shipped a first generative feature, built an evaluation set for it, and shared what you learned with the team.

By 6 months, you own our generative AI features, you have reduced inaccurate output in a measurable way, and you are guiding how we choose and use models.

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, Hugging Face 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!