Task Design Engineer

Role OverviewWe are looking for a SwarmBench Task Engineer specializing in planning and operations to design and build complex, multi-agent benchmark tasks that simulate real-world planning, scheduling, and operational decision-making scenarios. This role focuses on creating constraint-rich problems that evaluate multi-agent reasoning, decomposition, and optimization capabilities in realistic environments.What does day-to-day life look like?Design and develop multi-agent benchmark tasks involving:Planning, scheduling, and resource allocationOperational decision-making (project management, logistics, incident response, capacity planning)Create constraint-rich problem statements with multiple interacting variablesDevelop verification scripts to evaluate:Feasibility (all constraints satisfied)Completeness (all requirements addressed)Optimality (efficient solutions)Build decomposition strategies:Split tasks across specialized sub-agents (resource-based, constraint-based, conflict resolution, optimization)Model real-world operational scenarios with dependencies, timelines, and resource constraintsCollaborate on improving task quality, coverage, and evaluation rigorRequirements5+ years of experience in operations, project management, logistics, or supply chainStrong ability to formalize constraints, dependencies, and scheduling logicProficiency in Python for building verification and validation scriptsStrong structured problem-solving and decomposition skillsClear and precise technical writing skillsExperience with AI coding benchmarks (e.g., SWE-bench, Terminal-bench)Hands-on experience with Docker (Dockerfiles, image builds, debugging)RequirementsExperience with optimization techniques (linear programming, constraint satisfaction, scheduling algorithms)Background in operations researchExperience with simulation or modeling toolsKnowledge of AI planning systems or automated reasoningProject management experience or certifications (PMP, Agile, etc.)

Apply Now