Algorithmic Interception Strategy Lead

Air defense was built for single, expensive targets. Today it has to handle dozens or hundreds of cheap drones arriving at once. The hard part is the decision: how to assign limited interceptors to a crowded, fast-changing air picture, within seconds.

You'll lead our algorithmic answer to that challenge, from the first tracks in the air picture to the assessment of interception results. You'll combine classical optimization with models trained against adaptive swarms. The role reports to the program manager or chief architect.

Make swarm defense a solved decision problem. Your mission is to build the “brain” that turns a chaotic, saturated air picture into the right engagement plan in seconds: one that uses every interceptor wisely, adapts as the threat adapts, and earns the operator’s trust because it can explain itself. What you build will define how Israel’s defenders meet the next generation of aerial threats.

• Real-world impact: your algorithms go from simulation to field trials and directly shape how defense forces counter one of today's most urgent threats.

• Ownership: you'll lead the core decision layer of the system, with the freedom to decide where optimization ends and learning begins.

• Hard, unsolved problems: real-time optimization, adversarial multi-agent learning and human–machine trust, all in one role.

• Close to the mission: you'll work directly with the customer, operators and leadership, with a short path from idea to decision.

• Strong team: you'll work alongside senior engineers and researchers who care about getting it right, not just getting it done.

• Define the algorithmic concept and the multi-layer roadmap, and turn operational needs into testable requirements agreed with the customer.

• Lead the Weapon–Target Assignment core: real-time, uncertainty-aware, planned over time, cost-effective and explainable to the operator.

• Decide where learning belongs. Lead training of AI modules (RL/MARL, imitation of the optimal solver, adversarial red-team swarms), and make sure they run in real time on target hardware.

• Own the simulation environment, scenario library and training pipeline used to measure and improve performance.

• Align sensing, tracking and fusion, C2, interceptors, communications and CONOPS around one working concept, and present the results to the customer.

• An M.Sc. in CS, EE, mathematics or operations research.

• 10+ years developing algorithms for complex defense systems, including 3+ years of technical leadership across subsystems.

• Deep expertise in at least one of: combinatorial optimization; decision-making under uncertainty or RL; tracking and fusion; ML for decision-making (GNNs, transformers, learning-augmented optimization).

• Hands-on experience training deep learning models end to end (PyTorch or JAX).

• Strong Python plus C++ or Rust, and experience building simulation environments.

• The ability to lead through data and systems thinking, even without formal authority.

• Israeli citizenship and eligibility for a high-level clearance. Office-based in a classified environment, with travel for field trials.

• Operational air defense or C-UAS experience.

• Experience taking an algorithm or AI model from research to field trials.

• Publications in swarms, multi-agent RL or sensor fusion.

• Familiarity with Link-16, STANAG, JREAP and IAMD.

• Fluent technical English.