SwarmBench Task Engineer (Data Analysis) - 75113

About Turing:Turing is one of the world’s fastest-growing AI companies, accelerating the advancement and deployment of powerful AI systems. Turing helps customers in two ways: working with the world’s leading AI labs to advance frontier model capabilities in thinking, reasoning, coding, agentic behavior, multimodality, multilinguality, STEM, and frontier knowledge; and leveraging that work to build real-world AI systems that solve mission-critical priorities for companies.Role Overview:We are seeking experienced SwarmBench Task Engineers — Data Analysis to design and develop high-quality multi-agent benchmark tasks that evaluate the analytical reasoning, coordination, and execution capabilities of advanced AI systems.In this role, you will build realistic benchmark tasks that require AI agents to analyze large, messy, multi-source datasets, decompose work across specialist sub-agents, and arrive at specific, verifiable conclusions. These tasks may involve structured and semi-structured data such as CSVs, JSON files, logs, reports, survey results, vendor assessments, or financial and operational documents.Your work will help measure how effectively AI systems perform complex analytical workflows involving cross-referencing, contradiction detection, anomaly identification, and statistical reasoning across multiple data sources.What does day-to-day look like:Design and author multi-agent benchmark tasks centered on complex data analysis workflowsCreate realistic synthetic datasets or curate real-world style datasets across domains such as finance, operations, security, or market analysisBuild tasks that require agents to perform cross-referencing, anomaly detection, contradiction identification, and statistical computation across multiple sourcesDevelop decomposition guides that split analytical work across specialist sub-agents such as financial, technical, security, or operations analystsWrite precise oracle logic or verification scripts that validate specific analytical conclusions rather than generic summariesCreate reproducible evaluation environments using Python and DockerReview task performance signals to ensure strong separation between weaker and stronger agentic systemsRefine tasks to improve determinism, clarity, difficulty, and scoring qualityRequirements:5+ years of experience in data analysisStrong proficiency in SQL and Python for data analysis and scripting (pandas, NumPy, or similar)Experience working with real-world, messy datasets (CSV, JSON, logs, reports)Ability to design non-trivial analytical questions with clear, specific, and verifiable answersSolid understanding of statistical concepts (averages, distributions, outliers, correlations)Familiarity with AI coding benchmark environments (e.g., SWE-bench, Terminal-Bench)Comfortable working with Docker (writing Dockerfiles, building images, debugging containers)Perks of Freelancing With Turing:Work on cutting-edge AI projects with leading foundation model companiesCollaborate on high-impact work at the frontier of LLM evaluation and reasoningRemote, flexible opportunities with global teamsOffer Details:Commitments Required: 8 hours per day with a 4-hour overlap with PST.Employment Type: Contractor position (Note: this role does not include medical/paid leave).Duration of Contract: 4 weeks; [expected start date is next week].

Apply Now