Senior Software Engineer – Real-Time Conversational AI Platform

Build the real-time technology powering the next generation of AI conversations.

Our client, a fast-growing AI technology company in Japan, is looking for an experienced Senior Software Engineer to help build and scale its real-time conversational AI platform.

The company develops an AI-powered communication platform that enables businesses to automate and transform customer interactions using voice AI and conversational technologies. The platform has already been adopted by tens of thousands of business accounts and continues to grow rapidly.

As usage expands, the engineering team is facing increasingly sophisticated challenges around real-time communication, low-latency processing, scalability, reliability, and 24/7 availability.

In this position, you will become one of the key technical contributors behind the conversational platform, helping design the next generation of its architecture while raising engineering standards across the team.

What You Will Do

• Design and develop the core architecture of a real-time AI conversational platform
  
• Build and improve low-latency voice communication systems using Python, asyncio and WebSocket
  
• Improve the architecture and functionality of the AI conversation engine
  
• Design scalable and highly reliable APIs for a rapidly growing production environment
  
• Lead technical discussions and contribute to architecture and design decisions
  
• Conduct code reviews and design reviews to improve engineering quality across the team
  
• Identify technical debt and lead initiatives to improve system maintainability and performance
  
• Improve observability and reliability of real-time conversational systems
  
• Work closely with Product Managers and Designers to define technical specifications and deliver new product capabilities
  
• Integrate the platform with external services and APIs
  
• Leverage AI coding agents and modern AI-assisted development tools to improve engineering productivity
  
• Contribute to the evolution of the platform’s next-generation architecture
  

Technical Environment

Language: Python

Frameworks / Libraries: FastAPI, asyncio, WebSocket

Cloud & Infrastructure: AWS, Terraform, Amazon ECS

Databases: PostgreSQL, DynamoDB

External Integrations: Twilio, REST APIs

Development Tools: GitHub, GitHub Actions, Slack, Notion, Linear

Key Technical Challenges

This is not a standard backend engineering position.

The platform provides AI-powered voice conversations that must operate 24 hours a day, 365 days a year, making reliability and latency critical engineering challenges.

You will work on areas such as:

• Real-time bidirectional communication
  
• Persistent WebSocket connections
  
• Asynchronous processing
  
• Low-latency architecture
  
• High availability and fault tolerance
  
• LLM integration and redundancy
  
• Production observability
  
• Performance optimization
  
• Scaling real-time AI workloads
  

Requirements

Requirements

• 5+ years of professional Python development experience
  
• Experience developing and operating production services using web frameworks such as FastAPI
  
• Strong hands-on experience with asyncio, WebSocket, or similar asynchronous / persistent-connection technologies
  
• Experience designing and developing APIs with scalability and reliability in mind
  
• Strong understanding of software architecture, testing, maintainability, and production operations
  
• Ability to independently make technical decisions and take ownership from design through implementation and operation
  
• Japanese Business Level
  

Nice to Have

• Experience leading technical decisions within a Python engineering environment
  
• Experience defining architecture or engineering standards
  
• Professional experience with Twilio SDK
  
• Experience with performance tuning, profiling, and observability tools such as Datadog, New Relic, or OpenTelemetry
  
• Experience building high-availability or low-latency systems
  
• Experience with real-time voice or communication platforms
  
• Experience integrating LLMs or AI services into production systems
  
• Experience mentoring engineers through code reviews and architecture discussions
  

Who We Are Looking For

We are looking for an engineer who:

• Can independently make technical decisions in the Python ecosystem
  
• Enjoys solving complex engineering problems where there is no obvious answer
  
• Can act as a technical role model for other engineers
  
• Takes ownership beyond implementation, including architecture, testing, reliability, and operations
  
• Can balance product speed with long-term technical quality
  
• Communicates proactively with Product Managers, Designers, and other engineers
  
• Is excited about adopting new development approaches, including AI coding agents and AI-assisted engineering workflows
  
• Wants to build technology at the intersection of AI, voice communication, and real-time distributed systems
  

Why Join?

This is an opportunity to work on a technically challenging product where AI must interact with people in real time.

Rather than simply integrating an LLM into a conventional application, you will tackle engineering challenges involving milliseconds of latency, persistent connections, reliability, scalability and 24/7 availability.

You will have significant influence over technical decisions and help shape the architecture of a rapidly growing AI platform used by tens of thousands of businesses.

If you are a strong Python engineer interested in real-time systems, Voice AI, LLMs and highly scalable platforms, this is an opportunity to build technology that can fundamentally change how businesses communicate with their customers.

Benefits

Compensation

Annual Salary: 750万円～1,600万円 

Monthly salary: approximately ¥625K – ¥1.33M

Compensation will be determined based on experience and skills.

Stock options may also be offered depending on individual performance and contribution.

Location & Working Style

Tokyo or Osaka

• Hybrid / Remote work available
  
• Flexible working hours
  
• Core hours: 10:00 – 15:00
  
• Standard working day: 8 hours
  
• Full-time permanent position
  
• 3-month probation period with no change in compensation or benefits
  

Benefits & Holidays

• Five-day work week
  
• Saturdays, Sundays and national holidays off
  
• Paid annual leave
  
• Childcare leave
  
• Special / bereavement leave
  
• Full social insurance
  
• Remote / hybrid working environment
  
• Book purchase support
  
• Internal team events and other employee benefits