Remote SwarmBench Task Engineer (Contract)

About the role

Turing is seeking a Remote SwarmBench Task Engineer to design and build complex multi‑agent benchmark tasks that emulate real‑world planning, scheduling, and operational decision‑making. The role focuses on creating constraint‑rich problems to evaluate multi‑agent reasoning, decomposition, and optimization capabilities.

Key responsibilities

• Design and develop multi‑agent benchmark tasks covering planning, scheduling, and resource allocation.
• Create constraint‑rich problem statements with interacting variables.
• Develop verification scripts to assess feasibility, completeness, and optimality.
• Build decomposition strategies that split tasks across specialized sub‑agents.
• Model operational scenarios with dependencies, timelines, and resource constraints.
• Collaborate with the team to improve task quality, coverage, and evaluation rigor.

Required profile

• 5+ years of experience in operations, project management, logistics, or supply chain.
• Strong ability to formalize constraints, dependencies, and scheduling logic.
• Proficiency in Python for verification and validation scripts.
• Excellent structured problem‑solving and technical writing skills.
• Experience with AI coding benchmarks (e.g., SWE‑bench, Terminal‑bench).
• Hands‑on experience with Docker (Dockerfiles, image builds, debugging).

Required skills

• Python
• Docker
• Linear programming
• Constraint satisfaction
• Scheduling algorithms

What we offer

• Fully remote work environment.
• Opportunity to contribute to cutting‑edge AI projects with leading LLM companies.
• 40‑hour week with a 4‑hour overlap in PST.
• Contractor assignment (Freelance) for an initial 4‑week period, adjustable based on engagement.