Lead – Data Science & AI Engineering
Summary
Hands-on lead role building production ML/AI systems for logistics operations — turning data into predictions, anomaly detection and recommended actions for delivery teams. Core stack includes Python, statistical/ML modeling, AWS, Docker, APIs and MLOps/CI-CD practices.
Role
ShipDelight is building the next generation of logistics intelligence where on-ground operations are increasingly driven by data, prediction and recommended action rather than manual interventions. Our target operating model is :
Data → Detection → Context → Reason → Impact → Recommended Action → Intervention → Closure.
We are looking for a hands-on Lead – Data Science & AI Engineering who can bridge numerical data science, production engineering, MLOps/DevOps and logistics domain understanding. This person should be equally comfortable building a statistical/model-driven solution, understanding how it will run reliably in production and translating a real operations problem into measurable variables and decisions.
What we are looking for
- 4–5 years of hands-on experience in Data Science / Machine Learning / AI Engineering.
- Strong Python skills and experience with numerical/tabular datasets.
- Strong understanding of statistics, probability, regression/classification, tree-based models, anomaly detection, forecasting and scoring systems.
- Experience deploying ML models into production rather than only experimentation.
- Working knowledge of AWS/cloud infrastructure, Docker, APIs, CI/CD, monitoring and MLOps practices.
- Ability to understand infrastructure capacity, latency, scalability and cost implications of ML systems.
- Strong problem-framing ability — able to understand unfamiliar operational domains quickly and convert business behaviour into measurable data-science problems.
- Comfortable working directly with product managers, engineers, operations teams and senior management.
- Bias towards actionable intelligence over dashboards.
What success looks like
- Operational teams proactively receiving prioritised risks and recommended actions.
- Reduced manual analysis and firefighting.
- Models monitored for accuracy, drift, latency and business impact.
- A reliable and cost-efficient AI/ML production architecture.
- Clear evidence that data science is improving delivery performance, cost, risk, revenue protection or customer experience.