Senior Software Engineer, Generative AI Engineering

About Woven by Toyota

Woven by Toyota, a part of the Toyota Group, is challenging the current state of mobility through human-centric innovation and empowering mobility transformation. Through our AD/ADAS technology, our automotive software development platform Arene OS, our mobility test course Toyota Woven City, and Toyota’s growth fund, Woven Capital, we are pioneering the movement of people, goods, information, and energy, weaving a future of enhanced safety, connectivity and well-being for all.

=========================================================================

TEAM

The Generative AI Engineering team builds Generative AI based solutions that improves the productivity of users.

WHO ARE WE LOOKING FOR?

We are looking for a senior all-rounder engineer with LLM application experience and ambition — who can find and prototype GenAI-based solutions. You can develop these solutions into a functional and user-friendly web-based chat application. Additionally, you have experience deploying the application into enterprise platforms.

RESPONSIBILITIES

• Technical team leadership helping your coworkers level up their skills
• Advise on Generative AI strategy for Woven and beyond
• Develop web-based LLM-based applications including work on frontend (20%) , backend (60%) and DevOps (20%)
• Test modern LLM-based concepts such as chains, agents, entity memory, and prompt engineering
• Integrate existing systems to add amazing natural language-based user experiences
• This is a hybrid role requiring your presence onsite 3 days per week, where you will report to the group Engineering Manager.

MINIMUM QUALIFICATIONS

• B.S., M.S. in Computer Science, Electrical Engineering, or a related field
• Used or built applications powered by LLMs
• Experience with LangChain or similar LLM workflow frameworks; in particular building multi prompt workflows
• 5+ years as full-stack developer using Python and JavaScript/TypeScript
• 5+ years deploying applications to production environments including the ability to manage CI/CD pipelines, infrastructure as code, AWS resources, and k8s resources
• Experience as team lead

NICE TO HAVES

• Experience designing prompts using known and experimental prompt engineering techniques
• Experience building LLM-based agents
• Machine learning knowledge especially in NLP or Transformer models
• Experience with OpenAI API or GCP Vertex
• Stateful web applications using technologies such as React, Fast API, DynamoDB, Postgres, WebSockets, Server Side Events
• Fluent in Japanese

=========================================================================

Important Points

・All interviews will be arranged via Google Meet, unless otherwise stated.

・The same job descriptions are available in both English and Japanese; therefore, we kindly ask that you apply to only one version.

・We kindly request that you submit your resume in English, if possible. However, Japanese resumes are also acceptable. Please note that, depending on the English proficiency requirements of the role, we may request an English version of your resume later in the process.

WHAT WE OFFER

・Competitive Salary - Based on experience

・Work Hours - Flexible working time

・Paid Holiday - 20 days per year (prorated)

・Sick Leave - 6 days per year (prorated)

・Holiday - Sat & Sun, Japanese National Holidays, and other days defined by our company

・Japanese Social Insurance - Health Insurance, Pension, Workers’ Comp, and Unemployment Insurance, Long-term care insurance

・Housing Allowance

・Retirement Benefits

・Rental Cars Support

・In-house Training Program (software study/language study)

Our Commitment

・We are an equal opportunity employer and value diversity.

・Any information we receive from you will be used only in the hiring and onboarding process. Please see our privacy notice for more details.