AI Software Architect

Applied Materials•Santa Clara, CA

3d•Onsite

About The Position

Applied Materials is a global leader in materials engineering solutions used to produce virtually every new chip and advanced display in the world. We design, build and service cutting-edge equipment that helps our customers manufacture display and semiconductor chips – the brains of devices we use every day. As the foundation of the global electronics industry, Applied enables the exciting technologies that literally connect our world – like AI and IoT. If you want to push the boundaries of materials science and engineering to create next generation technology, join us to deliver material innovation that changes the world. We are seeking a deeply technical AI Software Architect located onsite at our Santa Clara, CA office to design, build, and scale an enterprise-grade AI-assisted software engineering platform that transforms how teams design, implement, test, review, and operate software. This role will create standardized agentic development workflows using modern AI coding assistants and automation agents, ensuring solutions are secure, governed, extensible, and measurable. The ideal candidate is a hands-on architect who can translate emerging AI capabilities into a repeatable, reliable developer platform—not ad-hoc experimentation.

Requirements

8+ years in software engineering, with significant experience in architecture or senior technical leadership roles.
Proven experience designing and scaling internal platforms, developer tooling, or distributed systems.
Strong understanding of modern SDLC, software architecture, CI/CD, and developer tooling ecosystems.
Hands-on experience implementing AI-assisted development workflows beyond basic chat usage, including:
Structured workflow design (prompt/playbook engineering)
Agentic orchestration patterns (planner/implementer/reviewer/tester roles)
Secure tool integration via a connector/protocol layer
Automated workflow triggers/hooks and enterprise governance controls
Proficiency in at least one backend ecosystem (e.g., Python, TypeScript/Java) and ability to deliver maintainable platform code.
Operates independently on ambiguous, high-impact technical problems.
Drives architecture decisions with clear trade-offs and production-ready prototypes.
Leads through influence, technical credibility, and enabling others.

Nice To Haves

Experience in DevEx, platform engineering, productivity engineering, or internal tooling.
Knowledge of AI security/compliance considerations (data governance, IP risk, policy enforcement).
Experience building evaluation frameworks for AI output quality, reliability, and safety.

Responsibilities

AI Development Platform Architecture (Core)
Architect an AI-assisted SDLC platform that embeds AI capabilities across: requirements → design → code → test → review → deploy → operate.
Define reference architectures and “golden paths” for AI-augmented engineering workflows (feature delivery, refactoring, modernization, incident response).
Design approaches for context management (large codebase understanding), long-horizon task execution, and multi-step planning.
Skill Packs / Playbooks Library (Reusable Workflows)
Build and govern an internal library of reusable “skill packs” / playbooks that encode best practices for repeatable workflows, such as:
PR review standards, unit/integration test generation, secure coding checks
Migration playbooks, runbook-driven operations, incident triage
Documentation generation (design docs, release notes, API docs)
Establish standards for skill-pack structure (instructions, templates, optional scripts/resources), versioning, quality checks, and safe rollout across teams.
Enable organization-wide distribution of approved skill packs to standardize engineering outcomes.
Extension System: Plugins, Commands, Sub-Agents, and Workflow Hooks
Design and package a vendor-neutral extension system that can bundle:
Reusable commands (shortcuts for common workflows)
Specialized sub-agents (e.g., planner, implementer, reviewer, tester, doc-writer)
Workflow hooks (event-driven automation at key lifecycle points such as pre-commit, post-merge, CI stages, or tool execution)
Create “team baseline bundles” that enforce consistent engineering practices (lint/test gates, structured reviews, changelog generation, security scanning).
Provide guidance and governance for safe installation, enable/disable toggling, and controlled rollout.
Tool Connector Protocol & Secure Integrations
Architect a standard connector layer/protocol that allows agents to securely interact with enterprise tools and data sources (repositories, CI/CD, ticketing, documentation systems, observability/logs, internal APIs).
Define policies for:
Tool allowlisting and permission boundaries
Authentication and secret handling
Audit logging, safe tool invocation, and error handling
Partner with security and platform teams to ensure integrations are compliant and enterprise-ready.
Desktop/Workspace Agent Workflows (Operational Automation)
Design and validate workflows where an AI agent can operate on local/approved workspace resources to:
Organize and transform engineering artifacts
Generate reports, release summaries, and project documentation
Automate repetitive operational workflows (triage, compliance evidence collection, runbook execution support)
Define boundaries, safe-usage patterns, and approval checkpoints for actions that modify files or operational state.
Hands-On Prototyping & Platform Delivery
Build production-quality prototypes and reference implementations demonstrating:
End-to-end agentic SDLC flows
Multi-agent collaboration patterns and orchestration
Integrations with developer environments, version control, and CI/CD
Drive platformization: convert prototypes into reusable components, internal services, templates, and documented patterns.
Measurement, Evaluation, and Continuous Improvement
Define measurable KPIs for AI platform impact, such as:
Cycle time / lead time, PR throughput, time-to-review, defect escape rate
Test coverage improvements, reduced rework, reduced incident MTTR
Developer satisfaction and adoption effectiveness
Implement evaluation loops for AI outputs: validation steps, automated checks, reviewer-agent patterns, and quality gates.
Build dashboards and reporting that tie adoption to tangible outcomes.