Yuma Watanabe
@yumawatanabe
AI coding-agent evaluator and red-teamer, turning adversarial tests into actionable reports to harden LLM safety.
What I'm looking for
I’m an AI coding-agent evaluator and red-teamer focused on adversarially testing AI coding agents and large language models. I design complex, multi-step and multi-turn instructions that probe reasoning, code changes, and tool use—especially where failures only surface under real difficulty and complexity.
In my contract role (remote), I directed AI coding agents to edit real, git-cloned repositories to expose weaknesses. I prioritize cross-file and cross-component consistency, identifying cases where edits look correct in isolation but break connections between components, then reproduce and document failure modes clearly so engineering teams can act on them.
I also build my own machine-learning models in Python, and I’ve applied that mindset to quantitative finance. In an independent project, I built a risk-focused swing-trading model using the moomoo/futu API, emphasizing minimizing maximum drawdown and validating with a 10-year backtest including look-ahead/data-leakage checks.
I’m a native Japanese speaker with B2-level English, and I enjoy multilingual adversarial evaluation where communication quality matters. I’m drawn to teams that value rigorous test design, structured technical documentation, and safety improvements grounded in measurable failure-mode evidence.
Experience
Work history, roles, and key accomplishments
AI Coding-Agent Evaluator & Red-Teamer
Vendor for Frontier AI Lab
Designed challenging, multi-step instructions to adversarially test AI coding agents editing git-cloned repositories, probing reasoning, code-change, and tool-use weaknesses. Reproduced and documented failure modes with actionable, cross-file consistency findings for engineering teams.
AI Coding-Agent Evaluator
Frontier AI Lab (Vendor)
Designed challenging multi-step, multi-turn prompts to adversarially test AI coding agents against real (git-cloned) repositories, probing reasoning, code changes, and tool use. Reproduced and documented failure modes with actionable reports focused on cross-file and cross-component consistency gaps.
Education
Degrees, certifications, and relevant coursework
Shibaura Institute of Technology
Bachelor of Science, Computer Science
Activities and societies: Focus on machine learning with quantum computing and optical communication; self-directed study in AI safety/adversarial evaluation and quantitative finance.
Pursuing a B.S. in Computer Science at Shibaura Institute of Technology. Focuses on machine learning with quantum computing and optical communication, with self-directed study in AI safety/adversarial evaluation and quantitative finance.
Tech stack
Software and tools used professionally
Availability
Location
Authorized to work in
Job categories
Skills
Interested in hiring Yuma?
You can contact Yuma and 600K+ other talented remote workers on Himalayas.
Message YumaGet matched with your dream remote job
Sign up now and join over 1,000,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
