About the role
Design, build, and optimize multi-step agentic workflows capable of multi-hop reasoning, hypothesis generation, and technical validation. Collaborate closely with mathematical researchers to translate complex, abstract proofs into structured technical specifications and automated pipelines. Main tasks listed: Design, build, and optimize multi-step agentic workflows capable of multi-hop reasoning, hypothesis generation, and technical validation; Collaborate closely with mathematical researchers to translate complex, abstract proofs into structured technical specifications and automated pipelines; Develop reusable architectural frameworks, tooling, and memory systems for STEM-focused AI agents; Evaluate and iterate on agent performance, ensuring high accuracy, reliability, and trace logic across execution steps.
Experience
Technical Expertise: Proven track record of architecting and deploying production-grade, multi-step agentic systems (e.g., using frameworks like LangGraph, AutoGen, CrewAI, or custom orchestration); Domain Experience: Background building AI/ML applications within STEM domains (Mathematics, Physics, Computer Science, or Quantitative Finance); Core Skills: Advanced Python proficiency, experience with LLM orchestration, structured output generation, tool integration, and state management; Problem-Solving: Comfort working alongside subject-matter experts to translate dense academic material into modular software systems
Selection process
Apply through the official Turing page (free account required). The listing does not describe further selection steps.
Eligibility
Not stated on the listing (remote)