System Architect, 3P Integrations, Agentic Product
Adobe · Municipalité San Francisco
Job description
About the role
Adobe is building a unified plugin and skills layer that brings Firefly, Photoshop, Lightroom, Premiere, Express, Acrobat and more into AI assistants such as ChatGPT, Claude, Gemini and Copilot. The System Architect owns the architecture of this plugin and leads technical partnerships with the companies building these assistants. The work covers protocol design, scale and the standards (MCP, A2UI and their successors) that will define how agents use creative tools.
Key responsibilities
- Own the plugin architecture: define the tools, resources and UI contracts that expose Adobe capabilities to third-party hosts, keeping one design working across hosts with different capabilities.
- Lead partner engineering: run the technical relationship with partner companies and internal product teams, shape integration contracts and pick the technical bets that differentiate Adobe.
- Build prototypes and demos with working code to settle architecture debates and speed up partner and leadership decisions.
- Optimize tools so models choose them correctly, set a high bar for latency and result quality, build evaluation suites and compatibility layers, and ensure observability and operational support at Adobe's scale.
- Lead engineers: set technical direction, run investigations, mentor engineers on MCP, agent harness, generative-UI patterns and AI-assisted development, and work with Firefly, Photoshop, Lightroom, Premiere, Express, Acrobat, platform, security, identity and trust and safety teams.
- Shape the standards and their adoption: stay ahead of model capabilities, frameworks and agent protocols, recommend when and how to adopt them, and represent creative and productivity use cases with proposals and reference implementations.
Required profile
- Shipped user-facing products used by millions, owning technical design across several connected services.
- Production work with the Model Context Protocol (tool design, servers and clients, auth flows, versioning).
- Familiarity with agent harnesses and generative UI such as A2UI, and with how large language models behave in production.
- Led technical partnerships or platform integrations with other companies, and led engineers as a technical lead or architect.
- Bachelor's degree in Computer Science or a related field, or equivalent experience; 12+ years building software, including several years in an architect or technical lead role.
- Nice to have: open standards or open-source involvement, a creative-tooling background, or work in the ChatGPT, Claude, Gemini or Copilot ecosystems.
Required skills
- Model Context Protocol (MCP)
- A2UI and agent harnesses
- Generative UI patterns
Expected pay range in the U.S. is $173,500 - $331,050 annually, depending on location and experience; in California it is $228,600 - $331,050. Some roles may be eligible for long-term incentives in the form of a new hire equity award.
Questions fréquentes
Why are you reporting this job?
Explore further
Salaries, guides and searches in the United States.
Salaries by job title
- Delivery Specialist 330
- Line Cook 264
- Restaurant Host 251
- Dishwasher 242
- Shift Supervisor 226
- Parts Specialist 208
- Retail Service Specialist 176
- Server - Red Robin 140
Apply in 30 seconds
Enter your email to apply. An account will be created automatically.
By continuing, you accept our terms of use.
Already have an account? Login
A question about this job?
Ask it here: you will get the full job summary by e-mail, right away.
Published 9 hours ago
Expires 1 month from now
4 views · 0 interested
Boost your chances
Upload your CV — we will match you with relevant openings.
Analyzing your CV...
Adobe
Municipalité San Francisco