Data Scientist

HT Digital Streams; Delhi; On-site; INR 1,800,000 - 2,400,000; Full time

Job summary

HT Digital Streams seeks a Senior Data Scientist to lead production-grade machine learning and deep learning initiatives. You will build and deploy models for affinity, propensity, and lookalike targeting, while collaborating with product, marketing, and engineering to deliver measurable impact.

The role requires hands-on experience with large datasets, end-to-end project execution, and exposure to Agentic AI, LLM-based workflows, and automation frameworks.

Qualifications

• 5+ years of experience in data science, machine learning, or applied AI roles.
• Strong hands-on experience with ML algorithms such as regression, classification, clustering, random forests, gradient boosting, XGBoost, LightGBM, CatBoost, and ensemble methods.
• Experience building propensity models, affinity models, lookalike models, segmentation models, and recommendation systems.
• Good understanding of deep learning concepts and practical exposure to TensorFlow, PyTorch, Keras, or similar frameworks.
• Strong programming skills in Python and strong SQL skills for working with large datasets.
• Experience with data science libraries such as pandas, NumPy, scikit-learn, statsmodels, XGBoost, and LightGBM.
• Experience with model evaluation metrics such as AUC, precision, recall, F1-score, lift, gain, KS, RMSE, MAE, and business KPIs.
• Understanding of feature engineering, feature selection, model interpretability, and model monitoring.
• Exposure to cloud platforms such as AWS, GCP, or Azure is preferred.
• Exposure to Agentic AI, LLMs, prompt engineering, RAG, LangChain, LangGraph, CrewAI, AutoGen, OpenAI APIs, or similar frameworks.
• Ability to communicate complex analytical concepts clearly to business stakeholders.

Responsibilities

• Build, validate, and deploy machine learning and deep learning models for business use cases.
• Develop affinity, propensity, recommendation, segmentation, churn, and lookalike models to improve targeting, personalization, and conversion.
• Work on end-to-end data science projects, including problem framing, data exploration, feature engineering, model development, evaluation, and deployment support.
• Analyze customer behavior, transaction patterns, content consumption, campaign responses, and digital engagement signals.
• Collaborate with product, marketing, business, and engineering teams to translate business problems into scalable data science solutions.
• Design experiments, A/B tests, uplift models, and measurement frameworks to assess model and campaign impact.
• Build scalable data pipelines and reusable modeling frameworks in partnership with data engineering teams.
• Apply deep learning techniques where relevant, including neural networks, embeddings, sequence models, NLP, or transformer-based models.
• Explore Agentic AI use cases such as AI assistants, workflow automation, autonomous task execution, and LLM-powered decision support.
• Present insights, model outcomes, and recommendations to technical and non-technical stakeholders.
• Mentor junior data scientists and help improve data science best practices.

Skills

Machine learning

Deep learning

Python

SQL

Model evaluation

Pandas

NumPy

XGBoost

LightGBM

CatBoost

A/B testing

Communication

Cloud platforms

Agentic AI

LLM workflows

Education

Bachelor's degree in CS/DS/Statistics/Engineering

Master's degree in a related field

AI/ML certifications

Tools

TensorFlow

PyTorch

Keras

MLflow

Airflow

Docker

Kubernetes

LangChain

LangGraph

OpenAI APIs

AWS

GCP

Azure

Job description

We are looking for a Senior Data Scientist with strong hands-on experience in machine learning, deep learning, predictive modeling, and customer intelligence models such as affinity, propensity, and lookalike models. The ideal candidate should be comfortable working with large-scale datasets, building production-ready models, and collaborating with business, product, engineering, and marketing teams to drive measurable impact. The role also requires exposure to Agentic AI, including AI agents, LLM-based workflows, tool-using agents, and automation frameworks.

Key Responsibilities

• Build, validate, and deploy machine learning and deep learning models for business use cases.
• Develop affinity, propensity, recommendation, segmentation, churn, and lookalike models to improve targeting, personalization, and conversion.
• Work on end-to-end data science projects, including problem framing, data exploration, feature engineering, model development, evaluation, and deployment support.
• Analyze customer behavior, transaction patterns, content consumption, campaign responses, and digital engagement signals.
• Collaborate with product, marketing, business, and engineering teams to translate business problems into scalable data science solutions.
• Design experiments, A/B tests, uplift models, and measurement frameworks to assess model and campaign impact.
• Build scalable data pipelines and reusable modeling frameworks in partnership with data engineering teams.
• Apply deep learning techniques where relevant, including neural networks, embeddings, sequence models, NLP, or transformer-based models.
• Explore Agentic AI use cases such as AI assistants, workflow automation, autonomous task execution, and LLM-powered decision support.
• Present insights, model outcomes, and recommendations to technical and non-technical stakeholders.
• Mentor junior data scientists and help improve data science best practices.

Required Skills and Experience

• 5+ years of experience in data science, machine learning, or applied AI roles.
• Strong hands-on experience with ML algorithms such as regression, classification, clustering, random forests, gradient boosting, XGBoost, LightGBM, CatBoost, and ensemble methods.
• Experience building propensity models, affinity models, lookalike models, segmentation models, and recommendation systems.
• Good understanding of deep learning concepts and practical exposure to TensorFlow, PyTorch, Keras, or similar frameworks.
• Strong programming skills in Python and strong SQL skills for working with large datasets.
• Experience with data science libraries such as pandas, NumPy, scikit-learn, statsmodels, XGBoost, and LightGBM.
• Experience with model evaluation metrics such as AUC, precision, recall, F1-score, lift, gain, KS, RMSE, MAE, and business KPIs.
• Understanding of feature engineering, feature selection, model interpretability, and model monitoring.
• Exposure to cloud platforms such as AWS, GCP, or Azure is preferred.
• Exposure to Agentic AI, LLMs, prompt engineering, RAG, LangChain, LangGraph, CrewAI, AutoGen, OpenAI APIs, or similar frameworks.
• Ability to communicate complex analytical concepts clearly to business stakeholders.

Preferred Qualifications

• Experience in digital, media, e-commerce, subscription, advertising, fintech, or consumer-tech domains.
• Experience with personalization, audience intelligence, marketing analytics, campaign optimization, or customer lifecycle modeling.
• Exposure to MLOps tools such as MLflow, Airflow, Docker, Kubernetes, Kubeflow, Git, and CI/CD pipelines.
• Experience with vector databases, embeddings, RAG pipelines, or LLM-based applications.
• Understanding of data privacy, responsible AI, model governance, and ethical AI practices.

Educational Qualification

• Bachelor's or Master's degree in Computer Science, Data Science, Statistics, Mathematics, Engineering, Economics, or a related field.
• Advanced degree or relevant certifications in AI/ML will be an advantage.
• Strong analytical and problem-solving mindset.
• Business-first approach to data science.
• Ability to work independently and manage multiple projects.
• Strong stakeholder management and communication skills.
• Curiosity to explore emerging AI technologies, especially Agentic AI and LLM-based systems.
• Ability to mentor and guide junior team members.