Machine Learning Scientist II

Machine Learning Scientist (MLS-2) – New Initiatives

About Nykaa

Nykaa is India’s leading beauty and lifestyle destination. We are a consumer-tech company offering a wide portfolio of beauty, personal care, and fashion products across online platforms and retail stores.

We are powered by technology and data, and our Data Science team plays a critical role in building intelligent, personalized, and seamless experiences for millions of customers. As we scale, we are investing heavily in foundational ML systems that enable real-time decisioning, automation, and GenAI-powered customer experiences.

Role Overview

MLS-2 (Machine Learning Scientist)

Key Responsibilities

1. Machine Learning & Modeling

• Build and improve forecasting models using statistical and ML techniques such as ARIMA, Prophet, XGBoost, LSTMs, and transformer-based architectures under guidance from senior scientists.
• Develop models for coupon optimization, price elasticity, uplift modeling, and marketing attribution to improve personalization and campaign efficiency.
• Contribute to fraud detection models using anomaly detection, graph-based techniques, and unsupervised learning.

2. Supply Chain & Operational Modeling

• Support the development of algorithms for inventory planning, SKU allocation, and warehouse optimization using linear/integer programming and heuristic methods.
• Work on improving Estimated Delivery Date (EDD) accuracy using spatiotemporal, carrier, and operational signals.

3. Data Science & Analytics

• Translate loosely defined business problems into structured ML tasks.
• Conduct exploratory data analysis, feature engineering, model training, evaluation, and documentation.
• Build and maintain data pipelines in collaboration with Data Engineering teams.

4. Deployment & Productionization

• Work with engineering teams to productionize ML models using frameworks like MLflow, SageMaker, Databricks, and Spark.
• Monitor model performance, detect drifts, and contribute to continuous model improvements.

5. Collaboration & Communication

• Collaborate with Product, Engineering, Operations, and Marketing teams to deliver data-driven insights and solutions.
• Present analysis and model outcomes to cross-functional partners in a clear and structured manner.

Qualifications & Skills

Experience

• 2–5 years

  of hands-on experience in Machine Learning, Applied Statistics, or related fields.

Education

• Bachelor’s or Master’s degree in Computer Science, Statistics, Applied Mathematics, Data Science, or a related quantitative discipline.

Technical Skills

• Strong foundation in ML concepts including regression, tree-based methods, regularization, bias–variance tradeoffs, and probabilistic modeling.
• Experience with time-series modeling (ARIMA, ETS, Prophet); exposure to deep-learning-based forecasters (LSTM, TFT, DeepAR) is a plus.
• Working knowledge of optimization techniques (linear programming, heuristics, or RL concepts) is desirable.
• Good coding skills in Python and experience with ML libraries such as Scikit-learn, XGBoost, PyTorch/TensorFlow, Prophet, and PyMC/Stan (nice-to-have).
• Experience working with distributed data environments like Spark, Databricks, or AWS is a plus.

Business Skills

• Ability to break down business problems into analytical tasks.
• Strong analytical reasoning and problem-solving skills.
• Clear written and verbal communication skills.

What You’ll Learn & Grow Into

• Building production-grade ML systems at scale.
• Designing optimization solutions for supply chain and logistics.
• Deep familiarity with causal inference and marketing science.
• Working with large-scale distributed data systems.
• Contributing to real-time decisioning systems and GenAI-powered experiences.

Qs to expect on:

• ML Foundational concepts like Bias-Variance Trade-Offs, Linear/Logistic regression, Tree Methods, Maximum likelihood Estimation, etc…
• Statistical foundational concepts like Central Limit Theorem, A/B testing, statistical distributions, etc.
• The Error/Cost functions behind the ML methods that you recently worked on, and intuitions behind them.
• Time-Series Forecasting methods,
  including classical (ARIMA, ETS) and modern DL based methods(DeepAR, etc.)
• Formulate Business problems as optimization problems with techniques from Linear/Integer Programming, Genetic Algorithms, Reinforcement Learning, and heuristic optimization.
• Observational Causal Inference Methods like Inverse Propensity Weighting, Doubly Robust Methods. Foundational concepts like Causal Assumptions, Potential Outcome Framework, etc.