Senior Software Engineer - AI & Agentic Architecture

In this senior individual-contributor role, you will combine hands-on software engineering with agentic frameworks and MCP or API-based integrations to design and ship agentic systems, developer tooling, and reusable platform capabilities.

Role Focus

You will work across the full lifecycle of agentic and AI engineering, covering discovery and prototyping through production delivery. The role includes technical leadership, mentoring, and collaboration with engineering teams to translate workflow needs into secure, reliable systems.

Key Responsibilities

• Design, build, and operate production-quality agentic applications using agentic SDKs or harnesses, including multi-agent orchestration, subagent delegation, tool integration, and lifecycle hooks.
• Design Model Context Protocol (MCP) tool and resource interfaces that enable coding agents or harnesses to access backend systems and enterprise data safely and reliably.
• Engineer prompts for dependable structured output, including JSON schemas, few-shot examples, and validation or retry loops, supported by evaluation frameworks to measure and improve output quality.
• Manage context across long documents, multi-turn conversations, and multi-agent handoffs, including escalation and human-in-the-loop patterns to improve production reliability.
• Configure and extend Codex or Claude Code for team-wide use, including AGENTS.md or CLAUDE.md hierarchies, custom slash commands, Agent Skills, path-specific rules, and plan mode.
• Integrate agentic development into CI/CD pipelines to automate code review, test generation, and PR feedback while minimizing false positives and duplicate findings.
• Build and maintain MCP server integrations (project- and user-scoped) that expand agent-native capabilities across engineering workflows.
• Identify high-value opportunities for AI-assisted development and develop reusable capabilities that multiple teams can adopt.
• Partner with engineering teams through hands-on discovery to understand workflows, pain points, and opportunities.
• Prototype and validate new AI capabilities with real users, then mature successful prototypes into secure, observable, maintainable production systems.
• Own implementation, testing, deployment, monitoring, and iteration for agentic systems.
• Provide hands-on technical leadership via architecture discussions, code reviews, and troubleshooting of agentic systems.
• Mentor engineers on agentic design patterns, prompt engineering, and agent-native development practices.
• Communicate tradeoffs, risks, and outcomes clearly to technical and non-technical stakeholders.
• Contribute to engineering standards, reusable patterns, and documentation that support other teams using agentic development tools.

Required Qualifications

• 6+ years of professional software engineering experience, including substantial hands-on work building and operating AI/LLM-powered or agentic applications.
• Strong programming skills in Java, Python, Go, Rust, or C++, with solid engineering fundamentals such as API design, testing, debugging, code review, and maintainable code.
• Production-grade experience with agentic SDKs or harnesses, MCP, and LLMs, including tool use, orchestration, RAG, context management, structured output, and evaluation.
• Experience designing MCP tool or resource interfaces, including tool selection reasoning, error handling, and reliability considerations for multi-agent systems.
• Demonstrated experience integrating AI into CI/CD and developer workflows.
• Ability to work in ambiguous problem spaces by evaluating tradeoffs and making pragmatic engineering decisions.
• Strong written and verbal communication skills, including experience mentoring and influencing decisions.

Preferred Qualifications

• Demonstrated expertise across agentic architecture, MCP integration, Codex or Claude Code configuration, prompt engineering, and context management.
• Experience building multi-agent research or customer support systems, or structured data extraction pipelines.
• Experience with AWS, Docker, Kubernetes, Terraform, and GitOps to support AI or agentic infrastructure.
• Familiarity with vector databases, embeddings, and AI evaluation frameworks.
• Contributions to open-source projects involving AI, agentic systems, or developer tooling.
• Strong systems thinking across models, agents, tools, context, APIs, data, and infrastructure, with the ability to reason about dependencies and tradeoffs across the stack.
• A track record of adapting quickly to new AI tools, models, and frameworks as the space evolves.

Technical Skills and Tools

• Java, Python, Go, Rust, C++
• Model Context Protocol (MCP), Codex/Claude Code
• AGENTS.md, CLAUDE.md
• JSON schemas, CI/CD
• RAG, LLMs
• AWS, Docker, Kubernetes, Terraform, GitOps
• Vector databases, embeddings

Location

Onsite: Aliso Viejo, CA, United States. (Location(s): United States, Aliso Viejo, CA)

Compensation

Base pay range: USD 177,300 - 265,900 per year. (Compensation (base pay range): $177,300—$265,900 USD)

Benefits

• Medical, dental, vision
• Matching 401(k)
• Paid time off
• Wellness program
• Employee discounts for Sony products
• Eligible for a bonus package

Job Details

• Experience: 6+ years
• Job ID: R-125588