ABOUT Aviation Innovation Research (AirLab)

The joint CAAS-Thales innovation lab known as ‘AIR Lab’ started to operate on 1st November 2019 with the objective to develop Proof of Concepts (POCs) or Minimum Viable Products (MVPs) of advanced and open technologies for future Air Traffic Management (ATM). Currently, the joint lab employs a team of 40 Thales engineers and 12 CAAS engineers and air traffic controllers operating in a vibrant ecosystem involving a number of Singaporean SMEs and start-ups, as well as key research institutes.

Thales engineers include 10 domain experts – with more than 10 years of experience – coming from Thales ATM centers of competence in France and Australia. These experts are coaching both the local Thales and CAAS engineers.

The POCs and MVPs are co-developed with the CAAS engineers who have access to the same development tools and environment used by the Thales Engineers (provided by the Singapore branch of Thales Digital Factory). The POCs and MVPs are defined in collaboration with CAAS air traffic controllers through iterative workshops.

AIR Lab research outcomes will feed the next generation of products, including clearly disruptive outcomes addressing Safety and Security for Open architecture, data driven ATM Twin, Green Aviation, Trajectory Based Operations.

As the AIR Lab was recently extended for another 3 years, 4 work streams are now embarked:

Regional Experimental Platform, FF-ICE/TBO, Green Aviation, Future-proof Interoperable Platform-Agnostic, Safe and Secure Platforms. These work streams are supported by the AIR Lab DataLake platform which provides data transformation and serving services in the cloud.

AIR Lab 2.0 continues to benefit from research conducted in Europe through new architecture research which, among other objectives, aims at meeting much stricter safety standards for ground ATM systems in development by the European Aviation Safety Authority (EASA). This breakthrough architecture study is co-funded by the French government (CASSIOPEA).

Regional Experimental Platform (REP) has been initiated in AIR Lab 1.0 and has the view to addressing regional needs in coordination with the SESAR 3 activities conducted in AMS France.

ROLE DESCRIPTION SUMMARY

As a Data Engineer in AIR Lab, you can independently take a use-case from raw data all the way to a deployed, monitored ML service—combining data engineering, modelling, and production MLOps while keeping business value front-of-mind. You should be someone who enjoys innovation and thinking outside of the box. You should be someone who enjoys working in a team of diverse people with multiple ethnic and cultural backgrounds. You should be someone who enjoys diving into the technical details of figuring out a problem and be able to communicate the solution back to the team so that the members can learn from it. You should be someone who loves learning new technologies and find innovative ways to apply newfound knowledge and be courageous to encourage fellow team members to be like you and enjoy participating in all aspects of engineering activities in the AIR Lab.

KEY ACTIVITIES AND RESPONSIBILITIES

As a Data Engineer, you are accountable for:

• Design and conduct exploratory data analysis to identify new ideas, hidden patterns, and opportunities for air traffic optimization.
• As opposed to other domains, the quantity of data in the aeronautical space is not huge, therefore thinking outside of the traditional ML boxes is essential to propose new AI solutions specific to that field.
• Focus on prediction models and algorithms (as opposed to detection of patterns).
• Design, develop, and deploy ML models for real-time classification, regression, and sequence prediction tasks using frameworks like PyTorch, TensorFlow, or Scikit-learn.
• Develop reinforcement learning agents using algorithms such as DQN, PPO, and Actor-Critic, and apply them to simulated and real-world environments via OpenAI Gym or custom setups.
• Work with state-of-the-art deep learning models, including transformer-based architectures, for sequence modeling and spatial-temporal problems.
• Build and automate machine learning pipelines using tools like Kubeflow, Airflow, or similar orchestration frameworks.
• Design reproducible workflows for data preprocessing, training, evaluation, and deployment.
• Integrate ML models into scalable APIs and deploy them to cloud-native environments using Docker and Kubernetes.
• Monitor model performance over time, retrain and iterate as needed based on live data and production drift.
• Maintain experiment tracking, model versioning, and reproducibility using tools like MLflow or Weights & Biases.
• Collaborate with DevOps and backend engineers to ensure seamless integration of ML components into larger systems.
• Maintain a high standard of code quality, documentation, and testing throughout all stages of the ML lifecycle.

KEY KNOWLEDGE AND EXPERIENCE

To be successful in your role, you will have demonstrated and/or acquired the following knowledge and experience:

Education

• Bachelors in Computer Science or Information Technology
• Masters degree in Computer Science or Data Science, if applicable

Essential Skills/Experience

• Aeronautical domain knowledge would be a major plus. At minimum, some experience in a domain that is not one of the common ones (vision, chatbots...).
• Experience in a domain where available historical data is not huge would be a plus.
• Good understanding of data (statistics, features, analytics) and how to map them to the domain.
• High level of core mathematic skills: algorithms (in particular for prediction), optimizations.
• 3-5 yrs delivering ML projects end-to-end (data prep to production).
• Proficiency in Python and machine learning frameworks such as PyTorch or TensorFlow.
• Solid understanding of reinforcement learning theory and experience with at least one RL algorithm (e.g. PPO, DQN).
• Practical experience with OpenAI Gym, Gymnasium, or equivalent RL environments.
• Familiarity with modern deep learning architectures — including transformers, attention mechanisms, or encoder-decoder models.
• Strong grasp of MLOps practices, including the use of Kubeflow Pipelines, MLflow, and model serving platforms.
• Experience deploying models in containerized environments using Docker and Kubernetes.
• Hands-on with ETL/ELT tooling (Apache Spark) and modern data-warehouse/lake (S3-based).
• Knowledge of CI/CD principles for machine learning workflows and model promotion strategies.
• Ability to build and debug data pipelines that support both training and inference workloads.

Desirable Skills/Experience

• Working knowledge of other languages (e.g., Python3, Scala2 or Scala3, Go, TypeScript, C, C++17, Java17)
• Familiar with designing and/or implementing AI/MLOps pipelines in public cloud (e.g., Azure, AWS, GCP)
• Exposure to LLM or RAG pipelines and prompt engineering.

Essential / Desirable Traits

• Possess learning agility, flexibility and pro-activity
• Comfortable with agile teamwork and user engagement