【AI】Senior Backend Engineer (AI Agent Framework)

About JAPAN AI

Geniee actively leverages AI technology in product development, offering features such as automatic meeting summarization and email generation using ChatGPT in its proprietary products, "GENIEE SFA/CRM" and "GENIEE CHAT," to enhance operational efficiency and productivity for clients.

In this context, the group established a new subsidiary, "JAPAN AI Inc.," on April 11, 2023, to further promote consulting for AI technology implementation, product provision, and research and development.

JAPAN AI Inc. is driven by the purpose of "preserving Japan and enhancing the potential of working individuals through AI." The company is committed to improving productivity and revitalizing industries in Japan by advancing research and development of cutting-edge AI technologies, including large-scale language models (LLM) and AI agents, and providing innovative products and solutions.

JAPAN AI Inc. : https://japan-ai.co.jp/

Why We’re Hiring

As we anticipate rapid business expansion, we are seeking a Senior Engineer who can lead research, development, and product implementation in advanced technical domains.

In particular, to accelerate research and large-scale development in the AI Agent domain, we urgently need to strengthen our team with engineers who can contribute to the development of core backend frameworks.

Position

Senior Backend Engineer (AI Agent Framework Team)
Role : Tech Lead or Member

You will be responsible for enhancing and optimizing the AI Agent Framework, which is utilized across our organization.

This position involves leading the implementation of complex features, such as a high-speed, scalable, multi-tenant runtime environment and interactions between multiple agents, while collaborating with internal and external development teams.

Responsibilities

As a Senior Backend Engineer, you will:

• Design and develop the AI Agent Framework:
  • Lead the development of core components, primarily in Python, to create a robust and scalable framework.
• Build architectures for agent collaboration:
  • Develop systems that enable seamless interaction and cooperation between AI agents, ensuring extensibility and adaptability.
• Implement and operate scalable runtime environments:
  • Create multi-tenant runtime environments optimized for real-time inference and performance in cloud-native settings.
• Collaborate with research teams:
  • Work closely with researchers to translate cutting-edge advancements in LLMs and AI Agents into practical product features.
• Lead the team:
  • Drive technical decision-making, improve development processes, and mentor other engineers to foster their growth.
• Optimize performance:
  • Continuously enhance system performance, ensuring reliability and efficiency in large-scale deployments.

This role offers the opportunity to work on groundbreaking technologies that push the boundaries of AI and software engineering.

Tech Stack

• Languages: Python (for framework development), TypeScript / React / Next.js (for frontend development)
• Infrastructure: GCP (containers / Kubernetes), Docker
• Tools: Slack, Confluence, Jira, Google Workspace, GitHub
• Work Environment: Mac (Apple Silicon), dual monitors available, access to AI assistants like in-house GPT tools and GitHub Copilot

Team Structure

We have approximately 30 engineers on the team, working collaboratively across multiple core development teams.

Why You’ll Love This Role

• Cutting-edge technology:
  • Work at the forefront of rapidly growing fields such as large-scale language models and AI agents, gaining hands-on experience with state-of-the-art technologies.
• High autonomy and agility:
  • Enjoy the flexibility and speed of decision-making unique to a startup environment, with the freedom to introduce and experiment with new technologies.
• Global team:
  • Collaborate with a diverse, multinational team of engineers, with opportunities for communication in English (positions not requiring Japanese proficiency are also available).
• Impactful work:
  • Play a pivotal role in shaping the future of AI-driven products, directly influencing the success of our clients and industries.
• Professional growth:
  • Take on leadership responsibilities, contribute to technical strategy, and grow alongside a team of highly skilled professionals.

Work Style

Hybrid work model: 3 days in the office, 2 days remote.
Flexible working hours: Core hours can be adjusted based on mutual agreement.

Minimum Qualifications

We are looking for candidates with:

• A bachelor’s or master’s degree in Computer Science or a related field, or equivalent practical experience.
• Practical experience in application development using Python (5+ years)
• Practical experience in machine learning (3+ years)
  • Machine Learning Algorithms : Basic understanding and implementation experience in regression, classification, clustering, etc.
  • Data Preprocessing : Skills in data cleaning, transformation, and feature engineering
  • Model Evaluation : Understanding and application of evaluation metrics such as accuracy, recall, and F1 score
• Practical experience in natural language processing (3+ years)
  • Text Processing Techniques : Experience using natural language processing libraries (NLTK, spaCy, Transformers, etc.)
  • Language Models : Experience in fine-tuning pre-trained models such as BERT, GPT, RoBERTa
• Experience with cloud platforms (AWS, GCP, or Azure) and container technologies (Docker, Kubernetes).
• Business-level communication skills in either English or Japanese (proficiency in one is required).

Preferred Qualifications

Candidates with the following experience or skills will be highly regarded:

• Development or research experience in AI/ML, chatbots, Generative AI, NLP, or agent frameworks.
• Expertise in distributed systems or performance optimization in large-scale data environments.
• Knowledge of multi-agent system design and implementation, including frameworks for agent collaboration.
• Experience in team leadership or management, or a strong desire to take on technical leadership roles.
• Practical experience working in multinational environments or overseas.

Selection Process

CV Screening → Multiple Interviews → Final Interview
(Reference checks are required before the final interview.)

Additional Information

This position will initially be hired by Geniee, Inc. and then seconded to JAPAN AI, Inc. (both companies share the same location and workplace).
There is a possibility of transferring to JAPAN AI, Inc. in the future.