The Role
Own ranking, relevance, and recommendation models for geo search, from training data and label pipelines through production serving. Build query understanding, cross-script matching, confidence models, offline evaluation, error analysis, and online A/B testing. Ensure models perform within strict latency requirements and remain reliable as data and cities change. Collaborate cross-functionally to improve search conversion, order conversion, and ranking quality across global markets.
Summary Generated by Built In
Geo Search runs the search that tens of millions of customers use to say where they are going, across many countries where the commercial maps everyone else leans on are often wrong, incomplete, or simply missing. We are building our own search and recommendation stack, which means we own the data, the ranking, and the measurement. The team is cross-functional, spanning backend, machine learning, mobile, and QA, and works with a product manager focused on relevance and with geo analysts. It owns place search and autocomplete, geocoding, ranking and personalization, location detection and pickup selection, and its own search screens on Android and iOS. It is measured on order conversion, search conversion, and mean reciprocal rank
We are looking for a Senior Data Scientist to own ranking, relevance and recommendation for geo search: the models that decide which places a customer sees, in what order, and how that changes with context.
We are looking for a Senior Data Scientist to own ranking, relevance and recommendation for geo search: the models that decide which places a customer sees, in what order, and how that changes with context.
This is a modeling role with production responsibility, and it is close to a founding one. You will define how relevance is measured here, build the training data from scratch, and own the models that follow. The interesting constraint is that suggestions must return within tens of milliseconds of each keystroke, in cities where map data is thin and people type in mixed scripts, so model choice is an evidence-based trade-off you will own rather than a preference: gradient-boosted ranking on behavioral data today, transformers and large language models where they earn their place in query understanding and cross-script matching, and neural reranking if the failure analysis justifies it. Ground truth comes from what drivers, couriers and customers actually do, and from completed rides, so a large part of the craft is turning messy behavioral logs into labels you can trust. You will measure your impact through offline evaluation and online A/B tests, and changes reach millions of customers in weeks.
Key Responsibilities
- Own ranking, relevance and recommendation for geo search end to end, from training data through to models serving in production
- Build the label pipeline that turns search sessions and completed rides into trustworthy training data, including correction for position bias and other presentation effects
- Train and own the models that order results, and the confidence model that decides per query whether we serve our own answer or fall back to an external provider
- Build query understanding for our markets, including cross-script matching, using large language models to label offline and distilling into models fast enough for the keystroke path
- Own evaluation end to end: the offline replay harness that scores recorded sessions against real rides, the error analysis that turns failures into work for the right team, and the online experiments that prove impact
- Keep models healthy after launch as data and cities shift
Skills, Knowledge and Expertise
Minimum qualifications
- 5 or more years building models that shipped and improved a production metric
- Direct experience with ranking, search relevance, or recommendation systems, including how they are evaluated
- Expert Python and SQL, fluency with gradient boosting, and working knowledge of transformers
- Experience taking a model to production and owning it afterwards
- The ability to work across teams, since search quality work generates data and engineering tasks that others own
Preferred qualifications - Depth in geocoding, autocomplete, or place search
- Learning to rank in practice: pairwise and listwise objectives, MRR, NDCG, Hit@k, and their failure modes
- Relevance tuning on OpenSearch or Elasticsearch, including analyzers
- Multilingual or cross-script search, for example Arabic and Arabizi or Urdu and Roman Urdu
- Distilling language models under a latency budget, and experience in mapping or geospatial products in developing markets
Conditions & Benefits
- Help us challenge injustice by creating fair choices for millions of people across 1100+ cities in 48 countries.
- Develop your professional skills with access to mentoring, career consulting, and learning programs.
- Collaborate with teams around the world and gain international experience through our Global Talent Exchange Program.
- Engage in company-wide challenges, awards, sports activities, employee-led social impact and volunteering projects.
- Work alongside people who take initiative, speak openly, and challenge themselves to grow.
- Improve your language skills through co-financed courses and internal speaking clubs.
- Annual salary from 70 700 EUR gross
Final benefits may vary depending on the location.
About
inDrive is a global tech company on a mission to challenge injustice through fair choices. We started in 2012 in the coldest city on Earth, when a group of friends created a way for people to agree on fair ride prices. That idea grew into one of the world’s top ride-hailing apps, now with 400M installs across 48 countries.Today, we offer more than rides: from freight and delivery to intercity travel and financial services, all designed to put people first. We are committed to having a positive impact on people’s lives both through our core business, which supports local communities via a fair pricing model; and through the work of our impact programs. Ready to ignite your inner drive?
Skills Required
- 5 or more years building models that shipped and improved a production metric
- Direct experience with ranking, search relevance, or recommendation systems, including evaluation
- Expertise in Python and SQL
- Fluency with gradient boosting
- Working knowledge of transformers
- Experience taking a model to production and owning it afterward
- Ability to work across teams and coordinate data and engineering tasks
- Experience with geocoding, autocomplete, or place search
- Practical learning-to-rank experience with pairwise and listwise objectives, MRR, NDCG, and Hit@k
- Relevance tuning on OpenSearch or Elasticsearch, including analyzers
- Multilingual or cross-script search experience
- Experience distilling language models under a latency budget
- Experience with mapping or geospatial products in developing markets
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
inDrive is a global IT and transportation platform inDrive is one of the world’s fastest growing online ride-hailing services. Its services are available in over 749 cities in 46 countries throughout the world. The Company’s app has been downloaded over 150 million times. inDrive offers other services, including intercity transportation, freight and cargo services, as well as delivery services in different markets of operations. inDrive is based in Mountain View, California, and operates regional hubs in the Americas, Asia, the Middle East, Africa and the countries of the CIS, and employs over 2,000 people. In early 2021, inDrive achieved unicorn status after closing a $140m investment round with Insight Partners, General Catalyst, and Bond Capital, which valued the company at $1.23 billion.
