Senior Software Engineer - AI & Agentic Architecture

Work as a senior individual contributor designing and shipping production agentic systems, developer tooling, and reusable platform capabilities.

Responsibilities

• Design, build, and operate production-quality agentic applications using agentic SDKs/harnesses, including multi-agent orchestration, subagent delegation, tool integration, and lifecycle hooks
• Define Model Context Protocol (MCP) tool and resource interfaces to provide coding agents/harnesses safe, reliable access to backend systems and enterprise data
• Engineer prompts for reliable structured output using JSON schemas, few-shot examples, and validation/retry loops; build evaluation frameworks to improve output quality
• Manage context across long documents, multi-turn conversations, and multi-agent handoffs; design escalation and human-in-the-loop patterns for production reliability
• Configure and extend Codex/Claude Code for team-wide use, including AGENTS.md/CLAUDE.md hierarchies, custom slash commands, Agent Skills, path-specific rules, and plan mode
• Integrate agentic development into CI/CD pipelines for automated code review, test generation, and PR feedback, with tuning to minimize false positives and duplicate findings
• Build and maintain MCP server integrations (project- and user-scoped) that extend agent-native development capabilities across engineering workflows
• Identify high-value opportunities for AI-assisted development and create reusable capabilities that multiple teams can adopt
• Partner with engineering teams to understand workflows, pain points, and opportunities through hands-on discovery
• Rapidly prototype and validate new AI capabilities with real users, then transition successful prototypes into secure, observable, maintainable production systems
• Own the full lifecycle: implementation, testing, deployment, monitoring, and iteration
• 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 results clearly to technical and non-technical stakeholders
• Contribute to engineering standards, reusable patterns, and documentation to help other teams build with agentic development tools

Requirements

• 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++ and solid engineering fundamentals (API design, testing, debugging, code review, maintainable code)
• Production-grade experience with agentic SDKs/harnesses, MCP, and LLMs including tool use, orchestration, RAG, context management, structured output, and evaluation
• Experience designing MCP tool/resource interfaces, including tool selection reasoning, error handling, and reliability in multi-agent systems
• Proven experience integrating AI into CI/CD and developer workflows
• Ability to work in ambiguous problem spaces and make pragmatic engineering decisions after evaluating tradeoffs
• Strong written and verbal communication skills, with experience mentoring and leading through influence

Technologies

• 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

Benefits

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

Preferred Qualifications

• Expertise across agentic architecture, MCP integration, Codex/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 for AI/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, including reasoning about dependencies and tradeoffs
• Track record of quickly adapting to new AI tools, models, and frameworks

Location

• Aliso Viejo, CA, United States (onsite)
• United States, Aliso Viejo, CA

Compensation

• USD 177,300 - 265,900 per year
• Base pay range: $177,300 - $265,900 USD

Job ID

• R-125588