Data Scientist II

Swiggy is hiring an experienced Data Scientist II to join its growing Data Science organization in Bengaluru. This opportunity is designed for professionals who enjoy solving real-world business problems through machine learning, advanced analytics, and statistical modeling. If you are passionate about building intelligent systems that directly improve millions of customer experiences every day, this role offers an excellent platform to work on large-scale production-grade AI solutions.

As a Data Scientist II, you will work at the intersection of business, engineering, and artificial intelligence. Your day-to-day responsibilities will go far beyond creating machine learning models. You will be expected to understand complex business challenges, convert them into measurable data science problems, develop scalable predictive models, validate their performance, and collaborate with engineering teams to deploy them into production.

One of the major focus areas of this position is improving advertising intelligence and recommendation systems. Modern digital advertising requires highly personalized recommendations, intelligent ranking systems, and optimized bidding strategies. Your models will help improve campaign performance while simultaneously enhancing user experience across Swiggy's ecosystem.

You will analyze massive datasets generated from customer interactions, delivery patterns, merchant activities, advertising campaigns, and platform engagement. These datasets contain valuable signals that can be transformed into actionable insights using machine learning, statistical inference, and optimization algorithms.

Your responsibilities will include designing complete machine learning pipelines starting from raw data collection to feature engineering, model training, hyperparameter tuning, evaluation, deployment, monitoring, and continuous improvement. Rather than working on isolated research projects, your solutions will directly influence live products used by millions of users.

Swiggy encourages engineers and data scientists to contribute beyond day-to-day development. Team members frequently share technical learnings internally, participate in conferences, publish engineering blogs, and contribute to the broader AI community. Candidates who enjoy knowledge sharing will find ample opportunities to grow professionally.

Key Responsibilities

• Build production-ready machine learning models for real business applications.
• Design scalable recommendation systems to improve user engagement.
• Develop intelligent ranking algorithms for advertisements and campaigns.
• Analyze large-scale customer datasets to uncover business opportunities.
• Perform feature engineering for structured and behavioral datasets.
• Create predictive models for personalization and optimization.
• Work closely with engineering teams to deploy models into production.
• Monitor model performance and continuously improve prediction accuracy.
• Conduct experiments and A/B tests to validate model improvements.
• Optimize campaign performance using advanced machine learning techniques.
• Collaborate with product managers during product planning.
• Build automated ML pipelines for faster deployment.
• Improve model latency, scalability, and reliability.
• Translate business problems into measurable machine learning objectives.
• Present technical findings to both technical and non-technical stakeholders.

Preferred Technical Experience

Candidates with hands-on experience in Python, SQL, TensorFlow, PyTorch, Scikit-learn, Spark, Hadoop, Kubernetes, Docker, feature stores, model monitoring tools, cloud-based ML platforms, and production deployment pipelines will have an advantage.

Why Join Swiggy?

• Opportunity to solve AI challenges at internet scale.
• Work on products used by millions of customers daily.
• Collaborate with highly experienced machine learning engineers.
• Exposure to modern recommendation systems and optimization algorithms.
• Strong engineering culture with ownership and innovation.
• Opportunity to publish research and engineering learnings.
• Fast-paced product environment with real business impact.
• Excellent career growth in Artificial Intelligence and Data Science.
• Competitive compensation and employee benefits.
• Learning-focused culture with continuous experimentation.

If you enjoy solving large-scale machine learning problems, building intelligent systems, and seeing your models create measurable business value, this role provides an exciting opportunity to grow your career while working on cutting-edge AI products.

Machine Learning

• Explain Bias-Variance Tradeoff.
• What is Regularization?
• Difference between Random Forest and XGBoost.
• How would you prevent overfitting?
• Explain Cross Validation.
• What evaluation metrics would you use for recommendation systems?
• Difference between Classification and Ranking models.
• Explain Gradient Boosting.
• What are Embeddings?
• Explain Feature Engineering.

Statistics

• Bayes Theorem
• Central Limit Theorem
• Hypothesis Testing
• P-value
• Confidence Interval
• A/B Testing
• Statistical Significance

SQL

• Window Functions
• CTE
• JOIN Types
• Ranking Queries
• Aggregations
• Query Optimization

Python

• NumPy
• Pandas
• Data Processing
• Object-Oriented Programming
• Decorators
• Multithreading Basics

Deep Learning

• CNN vs RNN
• Attention Mechanism
• Transformer Architecture
• BERT
• Fine-tuning LLMs
• Loss Functions

System Design

• Design a Recommendation System.
• Design an Ad Ranking Engine.
• ML Model Deployment Pipeline.
• Model Monitoring Strategy.
• Feature Store Architecture.

Machine Learning

A strong understanding of supervised learning, unsupervised learning, ensemble methods, and model evaluation is essential. You should know when to choose algorithms such as XGBoost, Random Forest, Logistic Regression, or Neural Networks depending on the business problem.

Statistics

Machine learning models rely heavily on statistics. Concepts like probability distributions, hypothesis testing, regression analysis, confidence intervals, variance, covariance, Bayesian statistics, and experimental design help in making reliable predictions and interpreting results correctly.

Python

Python is the primary programming language for most data science workflows. You should be comfortable with Pandas, NumPy, Scikit-learn, Matplotlib, TensorFlow, and PyTorch while also writing clean, maintainable production-ready code.

SQL

Data scientists spend a significant amount of time querying and transforming data. Advanced SQL knowledge including joins, window functions, aggregations, CTEs, indexing, and query optimization is expected.

Deep Learning

Understanding neural networks, backpropagation, transformers, embeddings, sequence models, and model optimization helps build intelligent systems capable of handling large-scale recommendation and personalization tasks.

Recommendation Systems

Modern platforms rely on recommendation engines to personalize user experiences. Learn collaborative filtering, content-based filtering, hybrid recommendation techniques, ranking models, and embedding-based retrieval methods.

Experimentation

Every model should be validated through controlled experiments. Knowledge of A/B testing, statistical significance, experiment design, and performance measurement is critical for production machine learning.

Communication

A successful data scientist explains technical concepts in business language, collaborates with engineers and product managers, documents findings clearly, and presents actionable insights to stakeholders.

• Keep your resume limited to one or two pages with a clean, ATS-friendly layout.
• Highlight production-level machine learning projects instead of academic assignments.
• Mention measurable outcomes such as improving prediction accuracy, reducing inference latency, or increasing business KPIs.
• Showcase expertise in Python, SQL, TensorFlow, PyTorch, Scikit-learn, and cloud technologies.
• Include links to GitHub, Kaggle, research papers, or technical blogs if available.
• Quantify achievements using numbers whenever possible, such as "improved recommendation CTR by 18%" or "reduced model training time by 35%."
• Mention experience with recommendation systems, ranking algorithms, or personalization if applicable.
• Add projects involving end-to-end ML pipelines, deployment, monitoring, and experimentation.
• Use keywords like Machine Learning, Deep Learning, Statistics, Recommendation Systems, Feature Engineering, Data Mining, Predictive Modeling, and A/B Testing naturally throughout your resume to improve ATS compatibility.
• Avoid generic skill lists without supporting projects or measurable accomplishments.
• Proofread carefully to eliminate grammar and formatting issues before submitting your application.