# Yuma Watanabe

Yuma Watanabe is a remote worker on Himalayas, AI Coding-Agent Evaluator & Red-Teamer at Vendor for Frontier AI Lab, based in Japan.

Source: https://himalayas.app/@yumawatanabe

```text
AI coding-agent evaluator and red-teamer, turning adversarial tests into actionable reports to harden LLM safety.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | Japan |
| Authorized to work in | Japan |
| Job categories | AI Coding Agent Evaluator, Red Teamer, Artificial Intelligence Security, Quantitative Trader, AI Security Researcher, Machine Learning Engineer, AI Safety Researcher, Quantitative Researcher, AI Coding Agent Evaluation, Coding Agent Evaluation, AI Coding Agent, AI Coding Agent Specialist, AI Agent Evaluation |
| Skills | Ethical Jailbreaks, Prompt Injection, Tool Abuse, Multi Turn Adversarial Elicitation, Failure Analysis, Model Evaluation, Technical Documentation, Python, API Integration, Quantitative Modeling, Git, Claude Code, Frontier AI Coding Agents, Risk Focused Swing Trading, Look Ahead Checks, Moomoo Futu API, Workflow Management |

## What I'm looking for

```text
I’m looking for a role where I can adversarially evaluate AI coding agents and LLMs, design rigorous regression-style tests, and turn failure modes into clear, actionable reports—while also building Python ML models and quantitative research.
```

## About

```text
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

### AI Coding-Agent Evaluator & Red-Teamer

Vendor for Frontier AI Lab

```text
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.
```

Skills: AI-Security, Red-Teaming, Ethical-Jailbreaks, Prompt-Injection, Tool-Use, Multi-Turn-Adversarial-Elicitation, Python, API-Integration, Quantitative-Modeling, Git

### AI Coding-Agent Evaluator

Frontier AI Lab (Vendor)

```text
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.
```

Skills: AI-Security, Red-Teaming, Ethical-Jailbreaks, Prompt-Injection, Tool-Use, Multi-Turn-Adversarial-Elicitation, Python, API-Integration, Quantitative-Modeling, Git, Claude-Code

## Education

### 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.

```text
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

- Claude Code
- Remote

To contact Yuma, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Yoshitaka Kurumada](https://himalayas.app/@yoshitakakurumada): Music Search Rating Evaluator, Appen
- [敏亮 俞](https://himalayas.app/@0002663): AI Software Engineer / SRE, Adventure, Inc. (Skyticket)
- [Александр Шульгин](https://himalayas.app/@Aleksandr_NFA): AI/LLM Backend Engineer, Independent
- [H O](https://himalayas.app/@hideyuki001): Senior AI Evaluator, Hansem Global
- [Nauman Mustafa](https://himalayas.app/@naumanmustafa): Sr. ML & AI Agentic Engineer, LegalOn Technologies
- [Believe Inpeace](https://himalayas.app/@believeinpeace): Data Scientist (Financial Risk Models), Yoii
- [Monika Srivastava](https://himalayas.app/@monikasrivastava): Senior QA Engineer, Peatix Japan
- [Shintaro Morita](https://himalayas.app/@shintaromorita): E commerce Seller / Independent Business Owner, Self employed
- [Justin Bouchard](https://himalayas.app/@justinbouchard): QE Software Engineer, Apple Inc
- [Khuong Rumo](https://himalayas.app/@khuongrumo): Computer Vision & Data Processing, Academic Project
