We are hiring an AI Engineer to build the AI features that help Upfynd run a large, accurate software directory. We write our own plain descriptions, sort products into the right categories and check every submission. You will build the tools that make that work faster and more consistent, with people always in the loop.
Why this role matters
AI can help a small team keep a huge catalogue tidy, but only if it stays accurate. A wrong category or an invented feature erodes trust quickly. Your work will make Upfynd faster to run while keeping every fact grounded in what a product actually says about itself.
What your week looks like
- Build LLM pipelines that draft neutral product descriptions from a product's own public information.
- Create classifiers that suggest categories and tags for new submissions.
- Detect duplicate listings and near-identical submissions using embeddings.
- Help moderators with AI-assisted checks for spam and low-quality submissions.
- Set up evaluations to measure accuracy, and add guardrails so the model never invents facts.
- Track the cost, speed and quality of LLM calls, and improve all three.
You will do well here if you have
- 2-4 years of software engineering, including hands-on work shipping LLM features.
- Strong Python and experience calling LLM APIs in production.
- Practical experience with embeddings and a vector database.
- Experience writing prompts with structured outputs and testing them properly.
- A careful mindset: you measure outputs instead of trusting them.
Nice to have
- Experience with LangChain, LlamaIndex or similar frameworks.
- Experience building human-in-the-loop review tools.
- Familiarity with FastAPI and Docker.
Your first 30, 90 and 180 days
- 30 days: You understand how listings are created and reviewed, and where AI could save the team the most time.
- 90 days: You have shipped a first AI feature to the moderation or catalogue team, with an evaluation set behind it.
- 180 days: You own AI-assisted cataloguing, with measurable gains in speed and accuracy and costs under control.
Where and how you will work
This is a full-time, onsite role at our office on the 11th floor of O-Hub, Infocity, Bhubaneswar. You will sit with the people you build with, which keeps decisions quick and conversations easy. Your everyday tools will include GitHub, Python, FastAPI, the LLM providers we work with and a vector database.
About Upfynd
Upfynd is a directory of new software, ranked by the people who actually use it. Every person gets one upvote per product, reviews come from real users, a person on our team checks every listing before it goes live, and nobody can pay to move up. Makers list and claim their products for free, and anything sponsored is clearly labelled and never touches rankings.
How to apply
Send us your CV along with links to AI projects you have built and how you checked their quality. Just like every listing on Upfynd, every application is read by a real person, and we reply to everyone who applies.
Skills and tools
- Python
- Large Language Models (LLMs)
- Prompt Engineering
- Embeddings
- Vector Databases
- LLM Evaluation
- FastAPI
- Docker