Data Scientist

Yulu; Bengaluru; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

Yulu, India’s largest shared electric mobility company, invites you to join a Bengaluru-based team solving optimization, ML, and analytics to improve city mobility. Formulate complex business problems as mathematical models and design scalable algorithms for matching, routing, pricing, and resource optimization under real‑world constraints.

You will deploy production-grade ML systems, build robust forecasting, graph learning, and decision-science tools to maximise system efficiency and user

Qualifications

• Strong foundation in probability theory, statistical inference, linear algebra, multivariable calculus, numerical optimisation, information theory, and statistical learning theory.

Responsibilities

• Formulate ambiguous business problems as mathematical optimisation and sequential decision-making problems under real-world operational constraints.

Skills

Probability & Statistics

Optimization

Machine Learning

Predictive Analytics

Graph ML

Reinforcement Learning

Time Series

Decision Science

Python

SQL

Tools

Python

SQL

Job description

Yulu is India’s largest shared electric mobility-as-a-service company. Yulu’s mission is to reduce traffic congestion and air pollution by running smart, shared, and small-sized electric vehicles. Yulu is led by a mission-driven & seasoned founding team and has won several prestigious awards for its impact and innovation. Yulu is currently enabling daily commuters for short-distance movements and helping gig-workers deliver goods for the last mile with its eco-friendly rides at pocket-friendly prices and reducing carbon footprint.

Yulu is excited to welcome people with high integrity, commitment, the ability to collaborate and take ownership, high curiosity, and an appetite for taking intelligent risks. If our mission brings a spark into your eyes and if you’dlike to join a passionate team that’s committed to transforming how people commute, work and explore their cities - come, join the #Unstoppable Yulu tribe!

Stay updated on the latest news from Yulu at https://www.yulu.bike/newsroom and on our website, https://www.yulu.bike/.

Role Summary

Optimization & Decision Science

• Formulate ambiguous business problems as mathematical optimisation and sequential decision-making problems under real-world operational constraints.
• Design scalable algorithms for matching, allocation, routing, scheduling, pricing, and resource optimisation across multi-objective environments.
• Develop optimisation frameworks that maximise long-term system efficiency, business value, and user experience while balancing competing objectives.

Machine Learning & Artificial Intelligence

• Design, develop, and deploy production-grade machine learning systems across supervised, unsupervised, self-supervised, probabilistic, and reinforcement learning paradigms.
• Develop robust feature representations and scalable learning architectures capable of operating on structured, temporal, spatial, graph, and high-dimensional datasets.
• Improve model performance through principled experimentation, rigorous validation, uncertainty quantification, and continuous model adaptation.

Statistical Learning & Predictive Analytics

• Develop statistically rigorous predictive models for forecasting, estimation, behavioural modelling, anomaly detection, risk assessment, recommendation, and ranking.
• Apply statistical inference to quantify uncertainty, estimate causal effects, validate model assumptions, and support evidence-based decision-making.
• Design models that remain calibrated, interpretable, and robust under changing data distributions and operational environments.
• Build forecasting systems for demand, supply, pricing, utilisation, capacity planning, and operational performance across multiple temporal and spatial resolutions.
• Develop probabilistic forecasting models capable of modelling trend, seasonality, uncertainty, structural breaks, and external drivers.
• Design adaptive forecasting pipelines capable of continuously learning from evolving data streams.
• Model complex relational systems using graph representations and network analytics.
• Develop graph-based learning algorithms for recommendation, matching, fraud detection, routing, community discovery, knowledge graphs, and network optimisation.
• Apply graph embeddings, graph neural networks, and representation learning to large-scale relational datasets.
• Develop intelligent decision-making systems where actions influence future system behaviour.
• Design algorithms that optimise long-term rewards under uncertainty while balancing exploration and exploitation.
• Apply reinforcement learning, contextual bandits, online learning, and sequential optimisation techniques where conventional supervised learning is insufficient.
• Develop machine learning solutions over spatial and spatio-temporal datasets.
• Model mobility patterns, spatial interactions, network coverage, route optimisation, and geographic demand dynamics.
• Build scalable geospatial representations that power prediction, optimisation, and operational decision-making.

Experimentation, Causal Inference & Scientific Evaluation

• Design statistically rigorous online and offline experiments to evaluate product, operational, and marketplace interventions.
• Estimate causal impact beyond conventional A/B testing while identifying confounding, selection bias, and treatment heterogeneity.
• Translate experimental findings into deployable decision frameworks with measurable business outcomes.

Applied Mathematics & Scientific Computing

• Apply principles from probability, statistics, optimisation, numerical methods, information theory, and linear algebra to derive efficient algorithms.
• Analyse computational complexity, convergence, numerical stability, approximation quality, and scalability of mathematical models.
• Develop mathematically principled solutions rather than relying solely on off-the-shelf machine learning techniques.

Research & Scientific Innovation

• Continuously evaluate advances in machine learning, optimisation, artificial intelligence, operations research, and statistical learning.
• Prototype, benchmark, and productionise novel algorithms where they provide measurable improvements over existing approaches.
• Drive innovation through first-principles thinking, scientific experimentation, empirical validation, and rigorous quantitative analysis.

Qualifications

• Strong foundation in probability theory, statistical inference, linear algebra, multivariable calculus, numerical optimisation, information theory, and statistical learning theory.
• Demonstrated expertise in optimisation, machine learning, predictive analytics, graph machine learning, reinforcement learning, time series forecasting, and decision science.
• Experience designing and deploying production machine learning systems that operate reliably at scale and deliver measurable business impact.
• Proven ability to translate ambiguous business problems into mathematically rigorous models, scalable algorithms, and production-ready intelligent systems.
• Expert-level programming skills in Python and SQL with strong software engineering practices and experience writing efficient, maintainable, and production-quality code.
• Excellent analytical, problem-solving, and communication skills with the ability to collaborate effectively across engineering, product, and business teams.