Senior AI Engineer – Intelligent Manufacturing Optimization

About the role

We are seeking a highly skilled and innovative PhD Researcher in AI Optimization and Operations Research to spearhead the development of next-generation scheduling engines for advanced automated manufacturing equipment. In this role, you will tackle the Multi-Hoist Cyclic Scheduling Problem (MHCSP) for high-precision production line. This is a highly constrained, NP-hard problem requiring an expert who can seamlessly blend traditional mathematical optimization with modern Deep Learning and Reinforcement Learning architectures to achieve flawless, collision-free, and maximum-throughput operations.

Key responsibilities

• Develop, implement, and validate state-of-the-art algorithms to solve complex, multi-hoist cyclic scheduling problems on a shared linear track.

• Build hybrid architectures combining Exact/Heuristic Solvers with Deep Learning (e.g., using Deep Reinforcement Learning or Graph Neural Networks to accelerate search spaces or handle real-time dispatching).

• Formulate strict mathematical models capturing spatiotemporal constraints, including hoist collision avoidance, acceleration/deceleration curves, and tight chemical bounded-soaking time windows.

• Design real-time, resilient anomaly-handling and dynamic rescheduling mechanisms to handle line disruptions mid-cycle.

• Translate theoretical mathematical models into production-ready software engines (APIs) that interface with simulation environments and industrial control systems (PLCs).

About you

• PhD in Computer Science, Industrial Engineering, Operations Research, Applied Mathematics, or a closely related quantitative field.

• Proven research track record (publications in IEEE, IJPR, JMS, or similar top-tier OR/AI journals) focusing on automated manufacturing scheduling, multi-robot coordination, or combinatorial optimization.

• Deep expertise in Constraint Programming (CP) and Mixed-Integer Linear Programming (MILP) using commercial or open-source solvers (e.g., Google OR-Tools CP-SAT, IBM ILOG CPLEX, or Gurobi).

• Strong background in tailoring metaheuristics (Genetic Algorithms, Tabu Search, Simulated Annealing) and applying Deep Reinforcement Learning (DRL) to sequence-dependent optimization problems.

• Proficient in Python or C++ with experience utilizing scientific and AI libraries (e.g., PyTorch, DEAP, NumPy, Pandas).

• Experience building custom discrete-event simulators to test scheduling algorithms safely before physical deployment.