AI/ML Scientist (Applied Scientist)

Maersk; Bengaluru; On-site; INR 1,800,000 - 2,400,000; Full time

Job summary

Maersk is seeking an Applied Scientist to design, build, and maintain data-driven products that optimize container terminal operations. You will develop models for scheduling, routing, and equipment efficiency, and integrate them into production-grade software.

You will work in a technical team of ~50, collaborating closely with operations personnel to ensure models reflect real-world terminal behavior and deliver impactful insights for global trade.

Qualifications

• 5+ years of industry experience delivering technical or optimization solutions.
• PhD or MSc in quantitative field or equivalent depth.
• Production Python: delivering production-grade Python code integrating models into software.
• Systems-level problem solving to model bottlenecks and bottlenecks.

Responsibilities

• Design and deliver advanced terminal operations solutions including scheduling, routing, and equipment efficiency.
• Build operational tools for real-time terminal operations and strategic planning.
• Bridge between the physical yard and code, translating realities into mathematical models.
• Explain model rationale and results to non-technical stakeholders to drive adoption.
• Monitor model performance against real events and iteratively improve drift and accuracy.

Skills

Python

Optimization

Statistics

Machine Learning

Education

MSc/PhD in OR/IE/ML/CS

Tools

PuLP

OR-Tools

HiGHS

Gurobi

Job description

Data AI/ML (Artificial Intelligence and Machine Learning) Engineering involves the use of algorithms and statistical models to enable systems to analyze data, learn patterns, and make data-driven predictions or decisions without explicit human programming. AI/ML applications leverage vast amounts of data to identify insights, automate processes, and solve complex problems across a wide range of fields, including healthcare, finance, e-commerce, and more. AI/ML processes transform raw data into actionable intelligence, enabling automation, predictive analytics, and intelligent solutions. Data AI/ML combines advanced statistical modeling, computational power, and data engineering to build intelligent systems that can learn, adapt, and automate decisions.

A.P. Moller - Maersk

A.P. Moller – Maersk is the global leader in container shipping services. The business operates in 130 countries and employs 80,000 staff. An integrated container logistics company, Maersk aims to connect and simplify its customers’ supply chains.

Today, we have more than 180 nationalities represented in our workforce across 131 Countries and this mean, we have elevated level of responsibility to continue to build inclusive workforce that is truly representative of our customers and their customers and our vendor partners too.

The team - who are we:

You will join a technical team of around 50 people in APM Terminals, building the systems behind some of the world's leading container terminals — where the cranes move, the yard fills up, and the vessel is waiting.

What makes this work inspiring is how close it sits to the operation. Your models are not evaluated in isolation: they are discussed with the people who run the terminal and measured against what actually happens there. Getting that right is demanding, and it is what makes the results worth something.

Our backgrounds span operations research, simulation, machine learning, software engineering, and terminal operations themselves. Nobody here covers all of it, and that is deliberate — the most interesting problems tend to sit between two people's expertise.

Your Impact

You will be part of the APM Terminals technical team. As an Applied Scientist, you will have a key role in designing, building, maintaining, and iterating on data-driven products that directly impact terminal operations. This position offers a unique opportunity to apply your technical knowledge to create operational and strategic insights that are transforming container terminal operations globally. This is an exciting time to join a growing and dynamic team that solves some of the toughest problems in terminal operations and builds the future of container shipping. We offer a unique opportunity to impact global trade via world-leading container terminals.

Key Responsibilities

• Design, implement and deliver advanced solutions for terminal operations including container handling equipment efficiency, yard positioning strategies, vessel loading/unloading sequencing, and vehicle routing — contributing to system design, architecture, and solution design as new features take shape.
• Build both operational tools for real-time, day-to-day terminal operations and strategic models for long-term planning and decision-making.
• Act as the bridge between the physical yard and the code, translating messy, stochastic physical realities into logical mathematical models.
• Explain complex model rationale and results to non-technical terminal operators and leadership to build trust and successfully roll out solutions to production environments.
• Monitor model performance against actual physical terminal events, iteratively improving models to handle operational drift and increase effectiveness.

What You Bring (The “T-Shaped” Profile)

We are looking for hybrid problem-solvers. We do not expect you to know everything; rather, we want to see a solid technical foundation combined with real depth somewhere.

The Core Foundation (Required)

• Experience: We typically look for 5+ years of industry experience building and delivering technical or optimization solutions. This is a guideline, not a filter — a strong PhD, or exceptional demonstrated ability, can substitute for part of it. We do expect some industry experience: you should have shipped something real that people depend on.
• Education: M.Sc. or PhD in Operations Research, Industrial Engineering, Machine Learning, Statistics, Applied Mathematics, Computer Science, or a related quantitative field — or equivalent practical depth.
• Production Python: Track record of delivering production-quality Python code for data-centric applications, specifically integrating models (e.g. machine learning, optimization, simulation, or statistical logic) into functional software.
• Systems-level problem solving: You can observe a physical operational bottleneck, frame it mathematically, and objectively decide the best analytical tool to solve it.

Your Area of Expertise

We are looking for depth, breadth, or a mix of the two. Either works:

• Advanced depth in one of the areas below, or
• Solid working knowledge across two or more of them.
• Operations Research (OR): Depth in optimization modelling — LP, MILP, constraint programming, and/or metaheuristics, applied to problems like scheduling, sequencing, routing, bin packing, and resource allocation. Fluency implementing these in Python across open-source and commercial solvers (e.g. PuLP, OR-Tools/CP-SAT, HiGHS, Gurobi).
• Discrete Event Simulation (DES): Experience developing models for stochastic operational environments, and evaluating solutions against simulation.
• Statistical Modelling: Fitting and validating statistical models of operational behaviour — dwell time distributions, arrival processes, equipment cycle times — and applying them to capacity analysis, as inputs to simulation models, or for inference.
• Machine Learning / AI: Experience using AI/ML methods for operational problems or prescriptive analytics (e.g. stochastic optimization, reinforcement learning).

Nice to Have

• Container terminal operations, port logistics, or comparable operational environments with complex resource allocation and scheduling dynamics — container handling equipment, yard operations, or vessel operations.
• Material handling, manufacturing operations, or other domains involving physical asset optimization and sequencing problems.

Maersk is committed to a diverse and inclusive workplace, and we embrace different styles of thinking. Maersk is an equal opportunities employer and welcomes applicants without regard to race, colour, gender, sex, age, religion, creed, national origin, ancestry, citizenship, marital status, sexual orientation, physical or mental disability, medical condition, pregnancy or parental leave, veteran status, gender identity, genetic information, or any other characteristic protected by applicable law. We will consider qualified applicants with criminal histories in a manner consistent with all legal requirements.

We are happy to support your need for any adjustments during the application and hiring process. If you need special assistance or an accommodation to use our website, apply for a position, or to perform a job, please contact us by emailing [e-mail].

CORE SKILLS Data Analysis: The process of inspecting, cleansing, transforming, and modeling data to discover useful information, draw conclusions, and support decision-making Proficiency Level: Proficient Statistical Analysis: The process of collecting and analyzing data to identify patterns and trends, and to make informed decisions. Proficiency Level: Proficient AI & Machine Learning: The field of artificial intelligence (AI) involves creating systems that can perform tasks that typically require human intelligence. Machine learning (ML) is a subset of AI that uses algorithms to learn from and make predictions based on data Proficiency Level: Proficient Programming: Writing code to manipulate, analyze, and visualize data, often using languages like Python, R, and SQL. Proficiency Level: Proficient Data Science: A multidisciplinary field that uses scientific methods, processes, algorithms, and systems to extract knowledge and insights from structured and unstructured data. Proficiency Level: Proficient SPECIALIZED SKILLS Data Validation and Testing: Ensuring that data is accurate and meets the required standards before it is used in analysis or decision-making. Model Deployment: The process of making a trained machine learning model available for use in production environments. Machine Learning Pipelines: Automated workflows that manage the end-to-end process of training and deploying machine learning models. Deep Learning: A subset of machine learning involving neural networks with many layers, used to model complex patterns in data. Natural Language Processing (NLP): A field of AI that focuses on the interaction between computers and humans through natural language. Optimization & Scientific Computing: Using Mathematical techniques and computational algorithms to solve complex problems and optimize processes Decision Modeling and Risk Analysis: Decision Modeling and Risk Analysis are methodologies used to make informed, data-driven decisions under uncertainty, especially when multiple factors and possible outcomes need to be considered. Technical Documentation: Creating and maintaining documentation that explains the functionality, use, and maintenance of software or systems. Definition of Proficiency Levels: Foundational: This is the entry level of the skill, typically expected when starting a new role or working with the skill for the first time. You rely on strong manager support, coaching, and training as you build the capability to progress to higher proficiency levels. Proficient: This is the level at which you are considered effective in the skill. You demonstrate more than just functional competence — a...