AI Optimization Engineer

Our Warehouse Execution Software leverages advances in classical and modern optimization techniques to bring intelligent execution to the world of intralogistics and warehouse automation. We synchronize the discrete and low-level logistics related processes to create a real-time decision engine that drives labor and equipment at the highest efficiency. Our software provides customers the operational agility they need to efficiently handle the demands of an Omni-channel environment.We are looking for a highly motivated individual who can develop cutting edge algorithms using domain knowledge from Artificial Intelligence, Machine Learning, and Operations Research. The candidate should have a solid grasp of theoretical approaches to discrete optimization but also a practical mindset regarding the tradeoffs between solution complexity versus optimality, emerging versus proven techniques, and coding from scratch versus utilizing existing frameworks. Many of the problems we encounter are novel and have never been solved before, so creative, out-of-the-box thinking and a fondness for experimentation are a must. We also want someone who stays current with recent trends in AI/ML so our approaches remain the most robust and competitive in the industry. Finally, the role requires strong team and interdisciplinary collaboration to see products through the development cycle from beginning to end.

What we offer:

• Career Development

• Competitive Compensation and Benefits
• Pay Transparency
• Global Opportunities

Learn More Here: https://www.dematic.com/en-us/about/careers/what-we-offer

Dematic provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.

This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation and training.

Tasks and Qualifications:

This is What You Will do in This Role:

• Frame and solve variety of intralogistics and planning problems with advanced analytics and AI techniques.
• See solution through full development cycle from inception, to proof of concept, to MVP, to final product deployment. Ensure what is delivered meets business requirements.
• Work directly with real and synthetic data to train models and build data-driven solutions.
• Design and build simulation tools of intralogistics processes to train and test models.
• Design and build statistical forecasting and machine learning models.
• Learn and apply new tools, technologies, and industry best practices.

What We are Looking For:

• Master's or PhD in Computer Science, Artificial Intelligence, Operations Research, Applied Mathematics, Control Engineering, Industrial Engineering, or equivalent field.
• Fluency in at least one general purpose programming language. Python or Java preferred. Statistical or database languages also a plus: R, MATLAB, SQL, etc.
• Knowledge of Reinforcement Learning / Approximate Dynamic Programming: MDP, Monte Carlo, MCTS, TD, Dyna-Q, online vs. offline learning, exploration strategies (epsilon-greedy, optimistic initial values, UCB1, etc.), DQN, DDQN, Dueling DQN, DDPG, REINFORCE, A2C, A3C, PPO, TRPO, SAC, MARL.
• Knowledge of Control Theory: Optimal control, MPC, LGQ, Adaptive Control
• Knowledge of standard Machine Learning models and techniques: Linear regression, logistic regression, decision trees, SVM, kNN, ensemble learning, XGBoost.
• Knowledge of Deep Learning architectures and use cases: ANN, CNN, RNN, VAE.
• GCP Workflows, GCP Cloud Functions, GCP Cloud Run, GCP Cloud Build, Docker, GCP Vertex AI, GCP Pub/Sub messaging and event driven architecture, cloud authentication/security, AI model deployment and inference, Ray distributed cloud computing, Terraform, continuous deployment (CD).
• Experiment tracking with Neptune AI, reinforcement learning model training and evaluation, metadata and model logging, Ray for distributed cloud computing in GCP, RLlib for distributed reinforcement learning in GCP.
• Familiarity with some of the following AI and Data Science frameworks: Pandas, PyTorch, Tensorflow/Keras, MXNET, Scikit-learn, Matplotlib, Numpy, fast.ai, Tensorboard, Ignite, Weights & Biases, etc.
• 2+ years of experience, including academic experience, in any of the above.

Ways to Stand Out

• Experience with RL Frameworks: OpenAI Gym, Dopamine, RLLib, OpenAI Baselines, Stable Baselines, Garage, Coach, etc.
• Experience with simulation and modeling tools: AnyLogic, Arena, Panda3D, Simio, SimPy, etc.
• Familiarity with any software IDE: PyCharm, IntelliJ, Visual Studio, Jupyter Notebook, etc.
• Familiarity with Cloud Computing: GCP, Azure, AWS, Docker, Kubernetes, edge computing
• Other software engineering skills: Git, Anaconda, OOP, test-driven design, common design patterns, dependency management, and build tools.

Some positions in the U.S. may require vaccination against COVID-19. Where legally permitted or required, offers for such roles are contingent on the candidate providing proof of full vaccination against Covid 19 (currently one dose of the Johnson & Johnson vaccine or two doses of the Pfizer or Moderna vaccine). Candidates with medical issues or religious beliefs or practices that prevent them from getting the vaccine may request an exemption from the vaccine requirement.