MET scientist presso Syngenta Group

Company Description

About Syngenta
At Syngenta Group, we're a global community of 56,000 innovators across 90 countries, united by a 250-year legacy of agricultural excellence. As the world's most local agricultural technology partner, we create tailor-made solutions that transform farming while protecting our planet, driven by our commitment to innovation, ethics, and integrity. Through our inclusive environment and diverse perspectives, we pioneer breakthrough solutions for farmers, society, and future generations. Join our worldwide teams of agricultural pioneers in creating a more resilient and equitable food system for all. 

Job Description

Role purpose

Reporting to the MET data analytic lead, the role is to develop AI and data science product to answer to analytical requirement for engineering & manufacturing organization.

This role drives innovation and product development in Pune and fully integrates with existing platforms to drive synergies with P&S and DPI teams. She/He ensures quality delivery in time at full on analytical & AI products in line with customer needs. This role is key in delivering Artificial Intelligence & analytics strategy for manufacturing and engineering working in partnership with DPI, sites and engineering teams.

Accountabilities

1. AI/ML Product Development & Technical Innovation

• Design, develop, and deploy machine learning models (predictive, prescriptive, diagnostic) for manufacturing and engineering use cases
• Implement MLOps practices including model versioning, monitoring, and automated retraining
• Build scalable algorithms and integrate with analytical platforms (Seeq, cloud infrastructure)
• Scout and evaluate emerging AI/ML technologies, frameworks, and methodologies (deep learning, NLP, computer vision, time-series forecasting)
• Prototype and pilot cutting-edge solutions; conduct POCs to assess technical feasibility and ROI

2. Analytics Delivery & Platform Integration

• Translate business requirements into technical specifications, data models, and analytical architectures
• Develop analytics backlog with clear technical milestones and delivery timelines
• Integrate AI/ML solutions with DPI infrastructure, manufacturing systems, and digital platforms
• Support global Seeq deployment through technical implementation and optimization
• Build dashboards, APIs, and visualization tools for model outputs and insights
• Collaborate with data engineers on ETL pipelines, data quality, and ML infrastructure
• Ensure code quality, documentation, and adherence to software engineering best practices

3. Technical Consultation & Stakeholder Engagement

• Act as technical consultant on AI/ML methodologies, algorithm selection, and solution design
• Interface with Data Science Teams, AI/ML Engineering Teams, DPI Platform Teams, and Manufacturing/Engineering stakeholders
• Communicate technical concepts, model performance metrics, and analytical results to diverse audiences
• Drive analytics adoption through technical workshops, enablement sessions, and knowledge sharing

Qualifications

Knowledge, experience & capabilities

Critical knowledge

• Deep understanding of machine learning algorithms, statistical modeling, and AI techniques (supervised/unsupervised learning, deep learning, time-series forecasting, optimization)
• Knowledge of MLOps practices, model lifecycle management, and production deployment architectures
• Understanding of data analytics platforms (Seeq, OSIsoft PI, cloud analytics tools) and their integration with ML workflows
• Understanding of data engineering principles, ETL pipelines, data governance, and data quality management
• Familiarity with cloud architectures (AWS/Azure/GCP) and distributed computing frameworks
• Proficiency in Python/R and ML frameworks (scikit-learn, TensorFlow, PyTorch, XGBoost)
• Knowledge of version control (Git), code review practices, and software engineering principles
• Understanding of manufacturing data systems and industrial IoT data streams

Critical experience

• Minimum 2 years of hands-on experience in data science, machine learning, and AI development
• Experience of deploying production-grade ML models in manufacturing/industrial settings
• Experience with agile delivery, DevOps, and CI/CD practices for analytics solutions
• Demonstrated success in delivering measurable business impact through AI/ML initiatives (ROI, efficiency gains, predictive accuracy, quality improvements)
• Experience working with cross-functional teams (data engineers, IT, operations, business stakeholders)

Critical technical, professional and personal capabilities

• Analytical Thinking: Strong problem-solving, root cause analysis, and diagnostic capabilities
• Technical Communication: Translates complex ML concepts into business value and actionable insights for diverse audiences
• Self-Driven: Takes initiative, works independently, and drives solutions from concept to production
• Attention to Detail: Ensures model accuracy, data quality, and robust validation
• Continuous Learning: Stays current with latest research, tools, and industry best practices in AI/ML
• Curiosity & Innovation: Explores new techniques and challenges conventional approaches
• Collaboration: Works effectively with diverse technical and non-technical teams
• Adaptability: Comfortable with ambiguity, changing requirements, and iterative development
• Results-Oriented: Focuses on delivering value and measurable outcomes

Critical leadership capabilities

• Drives Technical Excellence: Sets high standards for code quality, model performance, and analytical rigor
• Fosters Innovation Culture: Encourages experimentation, learning from failures, and data-driven decision making
• Focuses on Customer Value: Understands operational pain points and delivers solutions that create tangible business impact
• Collaborates Across Boundaries: Bridges gaps between data science, engineering, IT, and operations teams
• Influences Through Expertise: Drives adoption and change through technical credibility and value demonstration

Critical success factors & key challenges

• Data Quality & Availability: Navigating inconsistent data quality, missing historical data, and fragmented data sources across manufacturing sites and systems
• Legacy System Integration: Connecting modern AI/ML solutions with legacy manufacturing systems (historians, MES, SCADA) that may have limited APIs or data accessibility
• Organizational Change Resistance: Overcoming skepticism toward AI/ML predictions and building trust in model outputs among operations teams accustomed to traditional decision-making
• Balancing Innovation with Delivery: Managing the tension between exploring cutting-edge AI techniques and delivering practical, production-ready solutions within business timelines
• Cross-Functional Coordination: Aligning priorities and timelines across multiple teams (data engineering, IT infrastructure, site operations, DPI) with competing demands and resource constraints
• Scaling Across Sites: Adapting and deploying ML solutions across diverse manufacturing environments with varying processes, equipment, and data maturity levels

Additional Information

Syngenta is an Equal Opportunity Employer and does not discriminate in recruitment, hiring, training, promotion or any other employment practices for reasons of race, color, religion, gender, national origin, age, sexual orientation, marital or veteran status, disability, or any other legally protected status. 

#LI-Hybrid

Innovations

• Employee may, as part of his/her role and maybe through multifunctional teams, participate in the creation and design of innovative solutions. In this context, Employee may contribute to inventions, designs, other work product, including know-how, copyrights, software, innovations, solutions, and other intellectual assets.