【RAG Engineer】AI Agent Development | Full Remote | JLPT N2 level

★RAG / Search Infrastructure Engineer (AI Agent Development)｜AI/NLP Company

• Business Level Japanese Required (N2 Level)

◆Flextime＆ Fully Remote Work

◆Start-up Company

◆Own Products/Services

◆Annual Salary：7 million ～ 15 million yen.

-------------【About the company】-------------

The company's mission is "to advance humanity by reinventing the mechanisms of value creation" and aims to create an environment where people can focus on creating new value through the use of natural language processing and AI technologies.

AI delivers information directly related to business operations, thereby enhancing the information sensitivity of the organization. In addition, the company offers two SaaS products: "Anews," which encourages the conception of business ideas and their development within the organization, and "Astrategy," a market research service that provides suggestions by structuring necessary information according to the organization and its operations.

Currently, its main target is major manufacturing R&D in Japan, and more than 30% of the Nikkei 225 companies have already adopted the system. In the future, starting with manufacturing R&D, the company plans to expand to domestic enterprise companies, then to Japanese companies as a whole, and even to global companies.

The company completed a Series C financing of 1.1 billion in August 2022.

In February 2024, they were selected for the "GENIAC (Generative AI Accelerator Challenge) Project" promoted by the Ministry of Economy, Trade and Industry and NEDO, and have begun to develop their own LLM with 100 billion parameters!

The company has grown to 100 employees and is looking for more personnel to achieve further growth!

-------------【 Job Description】-------------

【Current Challenges】

・The company is focusing on the initial growth of AI agents specialized in professional operations.

・In the development of a technical exploration agent, the company is building a RAG system that derives technical solutions from data on the scale of hundreds of millions of records. However, improving accuracy and performance remains a significant challenge for the user experience.

・When implementing measures to enhance accuracy and performance, technical solutions may involve infrastructure and data-level interventions—such as rebuilding OpenSearch indices or constructing and populating new data stores. Due to the massive volume of data involved, these tasks are highly difficult and tend to become bottlenecks in the development process.

・The company is seeking a professional who excels at handling data and infrastructure to join the team and accelerate the improvement of both accuracy and performance.

【Your Role】

You will be responsible for the improvement and construction of infrastructure and portions of the server-side applications, focusing primarily on the RAG and search domains within the company's products.

■Responsibilities

・Development related to building and improving the company’s RAG infrastructure (Key technologies: OpenSearch, Python batch processing, Ruby backend processing, AWS, VectorDB)

・Identifying bottlenecks in search performance and planning and executing improvements

・Development related to web service backends other than those listed above (Web API development and improvement, infrastructure development and improvement)

・Updating technology stacks and middleware as needed, and resolving architectural issues and technical debt

・Defining specifications and implementing solutions in collaboration with Product Managers (PdMs) and other engineers (e.g., application developers, web crawler developers)

・Designing, operating, and troubleshooting service monitoring in collaboration with the SRE team

*Scope of changes: General development-related operations

【Team Composition】

SaaS Product Engineering Unit: Approximately 20 members in total

Breakdown:

・Manager: 1

・EMs/Leaders: 4

・SREs: 2

・Total Engineers: Approximately 20 (including the above roles)

【Development Environment】

[Organizational Structure]

The development organization is divided into two teams, each responsible for a specific AI agent.

Each team consists of PMMs, PdMs, designers, and engineers, creating a structure that facilitates seamless integration between business strategy and development.

The teams also collaborate with BizDev and Natural Language Processing (NLP) researchers as needed to proceed with development.

[Languages/Frameworks]

Ruby on Rails, Python, Vue.js, TypeScript, Flutter, Terraform

[Databases / Middleware]

Aurora MySQL, OpenSearch, DynamoDB, Redis (※All AWS services are used)

[Infrastructure / Cloud]

AWS (ECS, Lambda, Step Functions, Batch, EMR, Serverless, Bedrock, Cognito, SNS, SQS, SES, IAM, CodeBuild, CodePipeline, CodeDeploy, etc.)

[AI / Machine Learning]

OpenAI, Azure OpenAI Service, In-house LLM, AWS Bedrock, Transformers, vLLM

[Development Environment / Operations]

Terraform (IaC), Datadog, Sentry, SendGrid

【Position Highlights】

・Gain experience building and improving RAG infrastructure for commercial products that handle massive datasets in the hundreds of millions

・Participate in the launch and initial growth phase of an AI agent

・Gain experience in the development and operation of commercial products that utilize generative AI technology at their core

-------------【 Requirements】-------------

【Required】

*Meet all of the following

・Experience building and operating search engines such as OpenSearch (including data and index structures)

・Experience in development and operations using cloud platforms (e.g., AWS, GCP, Azure)

・Experience investigating and improving database performance

・Experience implementing batch processing for data handling

・1+ year of continuous experience in the development and operations of a single service or product

【Prerferred】

・Experience implementing vector databases (including use within OpenSearch) or vector computation processes

・Experience building and operating RAG systems

・Experience working on search process improvements (e.g., refining search algorithms / quantitatively evaluating search accuracy)

・Experience collaborating with Product Managers and business stakeholders to develop and improve products

【Ideal Applicants】

・Ability to formulate questions independently and use technical expertise to define and structure challenges

・Passion for exploring technology and a commitment to developing expertise

・Sensitivity to business outcomes and the ability to collaborate with colleagues from other disciplines

【Others】

・Able to reside in Japan

・Able to communicate fluently in Japanese, including on technical development matters

*Required level: Business or higher

--------------------------------------------------

【Working Time 】

Flextime System

■Salary increase (twice a year / May and November)

【About remote work】

■Basically, fully remote work

Residence must be in Japan (no full remote work while residing overseas)

■Flexible remote/working options (no restrictions on the number of times you can come to the office)

Each employee works while using the system according to his/her own circumstances.

There are people who work full remotely from Sendai, Kyoto, Osaka, etc., people who enjoy working while on vacation, foreign nationals who return to their home countries for a few weeks to work, and people who mainly come to work, making for a diverse work style.

【Welfare】

■Customer facing allowance (flat monthly amount of 20,000 yen *included in monthly salary)

Free use for self-improvement and customer value improvement

(purchase of books/attendance at seminars/equipment, etc.)

■Lump-sum allowance for preparation for remote work (flat rate of 50,000 yen in the first paycheck)

Provided as an expense for preparation for remote work

【Others】

■Periodic health checkups (all paid by company)

■Influenza vaccination

■PC of your choice provided

■Free drinks such as water/coffee/carbonated drinks/alcohol provided at the office

■Office Glico installed

【Education and Skill Development】

■Onboarding for 5 days after employment is available

■Monthly study day system (for own skill improvement and learning purpose)

【Internal Communication】

■Weekly company-wide online meeting

■Monthly social gathering (offline, some online)

■Semi-annual kick-off (hybrid of online and offline meetings)

【Holidays and Vacations】

■123 days off per year

■Saturdays, Sundays and national holidays (2 days off per week)

■Year-end and New Year vacations

■Paid leave (granted at the time of employment *Number of days granted depends on the month of employment)

■Prenatal leave

■Childcare leave