Role Overview

SEPS is seeking a highly skilled and experienced AI-Native Staff Software Engineer to support the development of the applications that power the Sony Engagement Platform. In this role, you will design and build secure, scalable, and high-performing solutions that deliver exceptional user experiences across Sony's global ecosystem.

As a Staff Engineer, you will contribute to both front-end and back-end systems, playing a hands-on role in architecture, implementation, and technical leadership. You will operate as part of an AI-native tiny team, directing and governing AI agents across the full delivery lifecycle. You’ll collaborate closely with product managers, designers, and other engineering teams to build robust, maintainable applications. This is a dynamic opportunity for individuals who thrive in a fast-paced, innovation-driven environment and are passionate about solving complex challenges with clean, thoughtful code.

Responsibilities

• Architect, design and develop RESTful API Endpoints, ensuring high performance, scalability and maintainability.

• Collaborate closely with front-end engineers to build dynamic, responsive, and user-centric web applications that deliver seamless user experiences.

• Define robust data models and database schemas, and manage relational or NoSQL databases with a strong emphasis on data integrity and performance optimization.

• Direct and govern AI coding agents across the delivery lifecycle, setting context, reviewing agent-generated output, and enforcing SEPS delivery standards at every gate.

• Design and maintain agent workflows using agentic coding tools (Claude Code, Cursor, Copilot) and the AI-native development framework, ensuring structured, auditable, and high-quality delivery.

• Configure and maintain prompt engineering patterns, structured output schemas, with rules and guardrails to align agent behavior with SEPS platform standards.

• Trace, debug, and triage agent tool calls, prompt failures, and unexpected outputs, maintaining visibility into AI-assisted delivery at every stage.

• Create and maintain clear, comprehensive documentation for application architecture, design, configuration, and ongoing maintenance.

• Provide accurate task estimations and delivery timelines, contributing to effective sprint planning and execution.

• Participate in the on-call rotation, responding promptly to production issues and ensuring system stability and uptime.

• Mentor and support junior engineers, fostering a culture of AI-native ways of working, learning, and continuous improvement.

• Honesty, trustworthiness and ethical conduct are material requirements for the responsibilities outlined above. 

Minimum Qualifications

• 8+ years professional experience working with medium/large complex code bases

• Experience in Full Stack development

• Experience with one or more of the following programming languages: Java, Go, or Python

• Experience in REST API design and implementation

• Highly Proficient in HTML, CSS, the JavaScript ecosystem, and familiarity with popular frameworks like React, Angular, Ember, Jest, Babel, and TypeScript

• Knowledgeable in UI/UX design principles

• Demonstrated proficiency with AI-native coding tools (Claude Code, Cursor, or GitHub Copilot) as a primary delivery vehicle, not a productivity add-on

• Working knowledge of prompt engineering, context management, and structured output patterns

• Familiarity with agent development concepts, tool use, function calling, approvals, and workflow chaining

• Awareness of secure AI coding practices including prompt injection, sandbox basics, and access control

• Strong communication and interpersonal skills

• Desire to collaborate and to develop strong and positive team relationships

• Attention to detail, organizational skills, a strong work ethic and the ability to work independently.

Preferred Qualifications

• Bachelor’s degree in Computer Science or related field, or at least three years of proven experience in lieu of a degree

• Demonstrated ability to write clean, maintainable, and well-documented code.

• Database management, cloud technologies (AWS), and containerization (Docker, Kubernetes)

• Knowledge of React best practices

• Familiarity with DevOps tools and practices, including CI/CD pipelines

• Automated deployment tools (e.g. Terraform, Ansible, Jenkins)

• Experience with the AI-native development framework (e.g. BMad Method)

• Familiarity with MCP, A2A concepts, tool-connection patterns, and agent skill configuration

• Eval basics, writing test cases, applying LLM-as-judge concepts, and defining acceptance criteria for AI-generated output

• Experience tracing and debugging prompt chains, tool calls, and agent failures

• Understanding of hallucination reduction techniques, prompt caching, and model fallback strategies

• Excellent problem-solving skills and attention to detail

• Experience with Agile development methodologies such as SAFe, Scrum

Benefits:   

The anticipated annual base salary for this role is $220,000–$240,000 for the Los Angeles, CA office location and $200,000–$220,000 for San Diego, CA.

This position is eligible to be performed remotely, and compensation may vary based on geographic location. Remote salary offerings will be determined based on the candidate’s individual work location.ranges

The provided reanges do not include any other compensation components or other benefits that an individual may be eligible for. The actual base salary offered depends on a variety of factors, which may include as, applicable, the qualifications of the individual applicant for the position, years of relevant experience, specific and unique skills, level of education attained, certifications or other professional licenses held, and the location in which the applicant lives and/or from which they will be performing the job. 

#LI-AS1