Machine Learning / AI Optimization Engineer

Location: Lusail, Qatar

Department: Tech

• Develop and deploy machine learning and optimization algorithms powering Snoonu’s hybrid autonomous logistics platform, enabling intelligent coordination across human couriers, ground robots, and drones.
• Design and implement advanced optimization strategies for task allocation, routing, scheduling, and dispatch decision-making across a multi-agent fleet environment.
• Develop and train multi-agent reinforcement learning (MARL) models to improve fleet-wide coordination efficiency under dynamic demand and traffic conditions.
• Build demand forecasting and spatiotemporal prediction models using modern architectures (e.g., Transformers, temporal models, graph-based methods) to support proactive positioning and better resource planning.
• Develop energy-aware and environment-aware optimization models to improve battery utilization, charging schedules, delivery sequencing, and overall operational efficiency under Qatar’s climate constraints.
• Integrate ML optimization models into the Robotics-as-a-Service (RaaS) orchestration platform in collaboration with platform/backend engineers, ensuring reliability and low-latency decision making.
• Evaluate model performance using defined metrics such as routing efficiency, ETA prediction accuracy, fleet coordination latency, and energy impact—supporting TRL advancement and pilot readiness.
• Implement experimentation pipelines including offline benchmarking, simulation validation, and controlled field pilot evaluation to improve model accuracy and generalization.
• Support continuous learning and model lifecycle management, including monitoring, retraining strategies, and mitigation of model drift using operational datasets.
• Document model architecture, assumptions, validation results, and experimentation methods to support R&D reporting, internal knowledge sharing, and stakeholder alignment.

• Bachelor’s or Master’s degree in Machine Learning, Artificial Intelligence, Computer Science, Data Science, Operations Research, or a related field. (PhD is a plus for research-driven optimisation work.)
• 2–4 years of backend development experience, with strong hands-on Python/C++ expertise.
• Strong analytical and problem-solving skills with the ability to work on complex real-world robotics challenges.
• Research-oriented mindset and ability to translate experimentation into production-ready autonomy improvements.
• Ability to work effectively in cross-functional teams (robotics, embedded, platform/software, operations).
• Clear communication skills and ability to document technical work, trade-offs, and validation outcomes.
• High ownership and accountability for results, timelines, and engineering quality.
• Adaptability to fast-paced R&D environments involving prototyping, testing, and iterative development.
• Strong business context understanding, able to translate operational needs into technical solutions.
• Open to feedback and proactive in applying improvements suggested by senior engineers or tech leads.

• Strong foundation in Python, including OOP principles, design patterns, and writing clean, maintainable code.
• Experience building backend services using frameworks such as FastAPI, Flask, or Django.
• Ability to design, develop, and maintain RESTful APIs with proper error handling and logging.

• Experience using AWS services, such as Lambda, SQS/SNS, API Gateway, Step Functions, DynamoDB, RDS, S3, and CloudWatch.
• Experience designing event-driven and serverless architectures.
• Familiarity with IAM, environment configuration, and cloud security best practices.

• Strong proficiency in Python and experience using deep learning frameworks
• Hands-on experience in one or more of the following areas:
  • Reinforcement Learning (RL) and Multi-Agent Reinforcement Learning (MARL)
  • Optimisation and decision systems for routing, scheduling, dispatch
  • Time-series forecasting and spatiotemporal modelling
  • Graph Neural Networks (GNNs) for mobility and routing problems
  • Energy optimisation and predictive control techniques (MPC, hybrid ML+control)
• Strong understanding of evaluation methodologies, including metrics design, baselines, A/B testing, and offline/online validation.
• Experience working with large-scale datasets, feature engineering, and model deployment constraints.
• Familiarity with simulation environments, digital twins, or synthetic data generation workflows is a strong plus.
• Knowledge of real-time systems, streaming data pipelines, and ML model monitoring practices is an advantage.
• Experience in logistics, last-mile delivery, fleet routing, or mobility analytics is a strong advantage.