Lead Data Scientist

ecolab; India; On-site; INR 3,000,000 - 7,000,000; Full time

Job summary

ecolab is seeking a Lead Data Scientist to design, develop, validate, and operationalize ML and analytics solutions powering intelligent products and business capabilities. You will guide feature engineering, experimentation, validation standards, and production-readiness to ensure models are reliable and explainable in real-world environments.

You will mentor others, partner with data and software engineers, and drive end-to-end ML lifecycle from development to monitoring across Azure ML,

Qualifications

• 8+ years of experience in data science, ML, or advanced analytics with production ML exposure.
• Hands-on experience building and deploying production-grade ML models.
• Proficiency in Python and ML libraries (scikit-learn, pandas, NumPy, XGBoost, PyTorch, TensorFlow).

Responsibilities

• Lead design, development, evaluation, and deployment of ML models across use cases.
• Translate business requirements into analytical approaches, model strategies, and deployment plans.
• Build robust pipelines for data prep, feature engineering, model training, and validation.
• Operationalize production-grade ML solutions with focus on reproducibility and impact.
• Collaborate with data engineers and software engineers to integrate models into apps and APIs.
• Design and implement MLOps including experiment tracking, model versioning, CI/CD for ML, monitoring, drift detection.

Skills

Python

ML pipelines

MLOps

Azure

Databricks

Docker

Kubernetes

CI/CD for ML

Explainability

Tools

Azure Machine Learning

Databricks

MLflow

Azure DevOps

GitHub Actions

Docker

Kubernetes

Azure Functions

Azure Container Apps

Azure Monitor

Application Insights

Job description

ROLE SUMMARY

As a Lead Data Scientist, you will lead the design, development, validation, and operationalization of machine learning and advanced analytics solutions that power intelligent products and business capabilities. This role combines strong hands‑on expertise in model development with practical experience in MLOps, deployment, monitoring, and lifecycle management. You will work closely with product managers, domain experts, engineers, architects, and platform teams to turn business problems into scalable, production‑grade ML solutions. In addition to building models, you will guide feature engineering strategies, experimentation approaches, validation standards, and production‑readiness practices to ensure models are reliable, explainable, and maintainable in real‑world environments. This role is ideal for someone who is equally comfortable developing models, operationalizing them in production, and mentoring others to raise the maturity of data science and ML engineering practices across the team.

KEY RESPONSIBILITIES

• Lead the design, development, evaluation, and deployment of machine learning models for predictive, classification, recommendation, anomaly detection, forecasting, and optimization use cases
• Translate business and product requirements into well‑defined analytical approaches, model strategies, feature sets, evaluation methods, and deployment plans
• Build robust and reusable pipelines for data preparation, feature engineering, model training, validation, hyperparameter tuning, and model packaging
• Develop and operationalize production‑grade ML solutions with strong focus on reproducibility, maintainability, scalability, and measurable business impact
• Partner with data engineers and software engineers to integrate models into applications, APIs, workflows, and downstream business systems
• Design and implement MLOps practices including experiment tracking, model versioning, automated deployment, CI/CD for ML, monitoring, drift detection, retraining strategies, and rollback readiness
• Establish model performance baselines and monitor production behavior for accuracy, drift, latency, stability, explainability, and business outcomes
• Contribute to best practices for model governance, feature lineage, documentation, testing, interpretability, and responsible AI
• Guide technical decisions on ML solution design, operationalization patterns, and production support expectations
• Mentor other data scientists and ML engineers on modeling rigor, experimentation practices, and production‑readiness standards
• Contribute reusable assets such as feature templates, modeling utilities, evaluation frameworks, deployment patterns, and internal accelerators
• Work with tools and platforms such as Azure Machine Learning, Databricks, MLflow, Azure DevOps, GitHub, Docker, Kubernetes, Azure Functions, Azure Container Apps, Azure Monitor, and Application Insights (or equivalent platforms and tools)

Required Qualifications

• 8+ years of experience in data science, machine learning, applied AI, or advanced analytics, including strong experience delivering ML solutions in production or product environments
• Proven hands‑on experience developing and deploying production‑grade machine learning models, not just analytical prototypes or notebooks
• Strong expertise in supervised and unsupervised learning, including model selection, feature engineering, validation, tuning, and performance interpretation
• Strong proficiency in Python and common ML / data science libraries such as scikit‑learn, pandas, NumPy, XGBoost, LightGBM, PyTorch, TensorFlow, or equivalent frameworks
• Experience building end‑to‑end ML pipelines across data preparation, feature engineering, model training, evaluation, deployment, and monitoring
• Hands‑on experience with MLOps practices and platforms, including experiment tracking, model registries, deployment automation, CI/CD for ML, model monitoring, and drift detection
• Practical experience with tools such as Azure Machine Learning, Databricks, MLflow, Azure DevOps, GitHub Actions, Docker, Kubernetes, Azure Functions, Azure Container Apps, or equivalent MLOps and cloud platforms
• Experience working with feature stores, model registries, experiment tracking tools, and production model monitoring approaches
• Strong understanding of data engineering and model integration patterns, including working with SQL, batch pipelines, streaming data, APIs, and application services
• Familiarity with observability and operational tooling such as Azure Monitor, Application Insights, MLflow tracking, Datadog, or equivalent monitoring platforms
• Strong understanding of ML quality dimensions such as bias, overfitting, data leakage, model drift, explainability, reproducibility, and performance stability
• Ability to translate business problems into scalable ML solutions and guide them through the full SDLC from design through deployment and continuous improvement
• Proven ability to provide technical guidance, review modeling approaches, and