Software engineer
- Location
- San Francisco
- Type
- Full time
- Compensation
- $150k-$200k
- Posted
- 2 days ago
Join a team building useful software. Work closely with engineering and design to turn new ideas into products.
Find roles through people you trust, and message a verified founder or page admin about your interest.
People Empowerment AI is part of Woven City Management. We develop AI products that draw on people's experiences and knowledge to support learning, decision-making, and invention. Our goal is to deliver useful services for people working in Woven City, Inventors, Weavers (residents), and the wider Toyota Group.
Our team offers the opportunity to develop products in the setting of a real city, working closely with users and experts from different disciplines. In a small team, you will contribute from problem discovery through development and validation, refining products while seeing how they create value for people.
We are looking for an engineer who understands user needs and the meaning behind data, and can take AI-enabled products from design and implementation through improvement after launch. You will work with specialists in areas such as UX research and other stakeholders to validate usability and practical value, and develop services that people can continue to use.
Reporting to the team leader, you will proactively identify issues and drive design, implementation, and validation within your area of responsibility, guided by shared technical direction and priorities. We are looking for someone who makes effective use of reviews and support while considering data and AI output quality, user experience, and ongoing operations.
・Work with users and stakeholders, including UX research specialists, to clarify problems and intended value, and translate them into requirements and development tasks that can be implemented and validated
・Design and implement features that combine web applications, backend APIs, databases, and LLMs. Use existing shared platforms and improve usability, including interaction flows, response times, and error handling.
・Understand the meaning, context, and sources of Japanese documents and conversational data, and establish workflows for collecting, processing, and using them. Identify gaps and errors, and evaluate and improve the quality of data and AI outputs.
・Use user feedback and usage logs to evaluate AI output quality and usefulness. Feed evaluation results into development priorities and ongoing improvements.
・Prepare your area of responsibility for release, including testing, required reviews, monitoring, and incident response. Work with the tech lead and specialist teams, communicate issues and dependencies early, and follow through on release and subsequent improvements.
・Business travel to Susono may be required a few times per month, depending on business needs
・3+ years of professional experience designing, implementing, and testing software using languages such as Python or TypeScript
・Experience developing software with AI coding agents such as Claude Code, Codex, or Antigravity
・Experience developing web applications or backend services and contributing to their delivery to users and operational improvements
・Experience developing applications that use APIs and databases, and the ability to inspect and transform data using SQL or similar tools
・Experience implementing LLM-based applications or prototypes and evaluating and improving errors and variability in their outputs
・Experience defining requirements with users or cross-functional stakeholders and taking your area of responsibility through implementation and validation
・Native-level Japanese proficiency, with the ability to understand subtle nuances, implicit assumptions, and context in conversations and documents, and assess the quality of data and AI outputs
・Conversational-level English proficiency.
・Experience developing voice interactions, real-time processing, conversational agents, or retrieval-augmented generation (RAG)
・Experience using Databricks, or building data collection, processing, and reuse workflows on a data platform with consideration for data quality, provenance, and access permissions
・Experience developing AI evaluation datasets and criteria, and translating user feedback into quality improvements
・Experience taking prototypes into practical use, including release reviews, coordination with security and privacy stakeholders, and operational preparation
・A proactive approach to uncertain problems, with sound prioritization, a willingness to seek support, and the perseverance to follow through. An ability to learn from people with different expertise and from user feedback, and adapt implementation and ways of working accordingly.