ML Engineer at SyngentaGroup

At Syngenta, our goal is to build the most collaborative and trustworthy team in agriculture, providing top-quality seeds and innovative crop protection solutions that improve farmers' success. To support this mission, Syngenta’s Seeds P&S is seeking a ML Engineer in Pune.The Machine Learning Engineer designs, develops, and operationalizes scalable machine learning solutions that drive business value. This role requires end-to-end ownership of ML pipelines—from data ingestion and feature engineering to model training, deployment, monitoring, and optimization. The ideal candidate combines strong software engineering practices with deep ML expertise. Data Engineering & Feature Development: Build and maintain robust ETL/ELT pipelines using Databricks and PySpark. Design and implement feature engineering workflows; leverage Databricks Feature Store for reusability. Model Development & Experimentation: Develop ML models (regression, classification, clustering, time-series, NLP) using scikit-learn, XG Boost, Light GBM, PyTorch/TensorFlow. Conduct hyperparameter tuning and model selection using ML flow for experiment tracking and reproducibility. ML Ops & Production Deployment: Deploy models to production using Databricks Model Serving, AWS Sage Maker (if applicable), or custom Fast API/Flask endpoints. Implement CI/CD pipelines for automated testing, validation, and deployment (GitHub Actions, Jenkins, GitLab CI). Monitoring & Maintenance: Set up model monitoring dashboards to track performance, data drift, and concept drift. Implement alerting systems for anomalies, errors, and SLA breaches. Collaboration & Documentation: Partner with data scientists, analysts, product managers, and software engineers to translate business problems into ML solutions. Document architecture, workflows, model decisions, and trade-offs (accuracy vs. latency vs. cost). Core Technical Skills: Databricks: PySpark, Delta Lake, Databricks SQL, Feature Store, ML flow integration, cluster optimization. ML flow: Experiment tracking, model registry, model versioning, deployment workflows. SQL: Complex queries, window functions, CTEs, query optimization, database design. Python: Expert-level proficiency in Pandas, NumPy, Polars, scikit-learn, XG Boost, Light GBM, PyTorch/TensorFlow. Version Control: Git, GitHub/GitLab workflows, branching strategies, pull requests.