Data Science Intern

About Tripzy:
Tripzy is an AI-powered travel planning and concierge platform for India. We help Gen Z and young professionals discover off-beat destinations and plan complete trips, from itineraries to stays and transport. We are incubated at Bennett Hatchery Foundation, backed by Times Group, and are now scaling our product and user base.
About the Role:
The quality of our recommendations is what sets Tripzy apart from a generic chatbot. As a Data Science Intern, you will help us improve the data behind them and the logic that ranks and selects what users see. You will work directly with the founders on a live product with real users.
Key Responsibilties:
In the first phase:
Clean, structure and standardize our destination, stay and activity data
Integrate data from multiple sources (APIs, spreadsheets, public datasets) into a reliable pipeline
Build and test ranking and filtering logic for recommendations (vibe, season, distance, traveler type) and evaluate how well it performs
Experiment with LLM-based approaches such as prompt testing, embeddings and RAG prototypes
As you grow in the role:
Analyze user behavior and itinerary data (searches, itineraries generated, drop-offs, repeat usage) to find what works and what doesn’t
Use user feedback and engagement signals to continuously improve recommendation quality and personalization
Build and run experiments and A/B tests to measure the impact of changes to recommendation logic
Work on reducing LLM cost and latency through caching, smarter retrieval and better prompt design
Integrate and standardize data from booking partners, hotel and transport APIs, and vendor platforms as they come online
Build evaluation frameworks and metrics to track recommendation relevance and data quality over time
Contribute to the design of Tripzy’s data and AI roadmap, including more advanced personalization and agentic features
Requirements
Proficiency in Python, SQL and pandas
Basic understanding of machine learning and how ranking, similarity or recommender systems work
Curiosity about LLMs, embeddings and RAG
A GitHub profile or portfolio with at least one data or ML project
Strong attention to detail and the ability to work independently
Currently pursuing or recently completed B.Tech / BCA / MCA / Data Science or a related field
Good to Have
Experience with web scraping or working with APIs
Exposure to LLM APIs or graph databases
Interest in travel and exploring off-beat India
What You’ll Get
Hands-on experience on a live AI product, not a sandbox project
Direct mentorship and access to the founders
Real ownership of your work
Internship certificate and letter of recommendation
Possibility of a full-time offer for strong performers
Duration: [3-6 months]
Stipend: [Upto ₹2.5-3K per month]

Work arrangement
Hybrid