Lead Data Scientist · Dubai, UAE
I build the AI systems people actually keep using.
Nine years of production data science. From marketing science for global brands to production AI systems.
A model nobody uses is a model that did not happen.
I started in consulting, so I learned that early. Most of my career has been spent in the gap between “the notebook works” and “the business changed what it does.”
What that has produced
~29%
Search precision
More relevant results for AI agents, inside a sub-millisecond budget. No added latency.
−90%
Manual analysis
Weeks of reading customer reviews replaced by a ranked list of what to fix, with evidence attached.
40→23%
Customer churn
Measured against a permanent untreated holdout, on a base of five million customers.
Selected work
One from each layer I have worked at: the infrastructure other teams build on, the product a customer touches, and the decision a business makes with money.
01
Nebius: better answers, same speed
AI search relevance. The filtering layer that decides which search results are worth putting in front of an AI assistant.
Search & ranking · Applied ML · Latency engineering
~29% more precise,
no added latency
Read the case →
02
Momos: review replies in minutes
Automated customer replies. An AI that writes on-brand answers to public reviews, and reliably refuses to touch the sensitive ones.
Generative AI · RAG · Human-in-the-loop design
routine cases handled
without a person
Read the case →
03
Yum! Brands: pricing backed by evidence
Menu pricing and promotions. The models and the simulator behind pricing decisions for Pizza Hut and KFC in three markets.
Price elasticity · Marketing mix modelling · C-level advisory
Pizza Hut & KFC ·
Canada, Brazil, UK
Read the case →
How I work
01
Agree upfront on what proves the idea wrong.
02
Never ship without an evaluation.
03
Give stakeholders something they can poke at.
Background
Marketing science → AI product → AI infrastructure. Four companies, five industries, one discipline. Founders and C-level stakeholders in every role; teams of three to four.
Oct 2025 – May 2026
AI infrastructure
Nebius (acq. Tavily) Lead Data Scientist · Abu Dhabi
The layer other teams build agents on: search relevance inside a sub-millisecond budget, a versioned revenue platform at a million records a day, and twelve-month forecasting with scenario simulation.
May 2022 – Sep 2025
AI product
Momos Lead Data Scientist (AI) · Abu Dhabi
Took LLM products from prototype to production for multiple brand clients: a guarded RAG response agent, AI Insights, and the LLM stack migration behind both. Led teams of three to four.
Aug 2017 – May 2022
Marketing science
Yum! Brands & Kvantum Lead / Senior Data Scientist · Delhi
Pricing and promotion analytics for Pizza Hut and KFC across Canada, Brazil and the UK, reporting into the Chief Analytics Officer. Before that, four years of consulting on marketing mix modelling, attribution and retention for brands across CPG, retail and pharma.
Notable brands
Some I worked with directly on pricing and marketing science. Others I reached through the AI products I built, where the brand count runs into the hundreds.
QSR, direct
CPG, pharma & retail, direct
Reynolds
Through product at Momos
and several hundred more
Toolkit
Applied AI & ML
LLMs, RAG, agentic systems, prompt engineering, forecasting, segmentation, uplift modelling, churn, price elasticity, marketing mix modelling, XGBoost, CatBoost, neural networks, SHAP
Data engineering
Python, SQL, PySpark, Snowflake, BigQuery, Databricks, Airflow, AWS Lambda, Azure Data Factory, Docker, FastAPI, CDC, SCD2, Tableau, Power BI, Omni
Search & measurement
BM25, hybrid retrieval, ranking and reranking, Elasticsearch, pgvector, evaluation harnesses, A/B testing, convex optimisation, simulation, Kalman filters
Education
Post Graduate Diploma, Applied Statistics IGNOU, Delhi
B.Tech, Computer Science Engineering GGSIPU, Delhi
Certifications
AI Agents in LangGraph · DeepLearning.AI
Building & Evaluating Data Agents · DeepLearning.AI
Hiring for data, ML, or AI systems?
Immediately available, based in Dubai, and I reply fast. Happy to walk through any case in detail - the decisions, the trade-offs, and what I would do differently today.