Operations Engineer – Multi‑Agent Benchmark Tasks (Remote)

About the role

This contract position focuses on designing and implementing benchmark tasks for multi‑agent systems. You will translate real‑world operational challenges—such as logistics, project management, and incident response—into structured, constraint‑rich problem statements.

Key responsibilities

• Design and develop multi‑agent benchmark tasks involving planning, scheduling, and resource allocation.
• Create realistic operational scenarios with timelines, dependencies, and resource constraints.
• Build constraint‑rich problem statements and break complex problems into structured sub‑tasks.
• Develop Python scripts to evaluate feasibility, completeness, and optimality of solutions.
• Collaborate with cross‑functional teams to improve task quality, coverage, and evaluation rigor.

Required profile

• Strong experience in operations, project management, logistics, or supply‑chain domains.
• Deep understanding of constraints, dependencies, and scheduling logic.
• Proficiency in Python for validation and verification scripting.
• Excellent structured problem‑solving and technical documentation skills.
• Ability to work in a fast‑paced environment and meet tight deadlines.

Required skills

• Python
• Docker
• Linear programming and constraint‑satisfaction techniques
• Scheduling algorithms
• Simulation or modeling tools
• AI planning systems or automated reasoning
• Familiarity with AI benchmark suites (e.g., SWE‑bench, Terminal‑bench)

What we offer

• Short‑term (4‑week) contract
• $15 per hour
• Remote work with 20–40 hours/week and a required 4‑hour overlap with PST