Principal Machine Learning Engineer, Agent Harness - Meta Factory

Adobe Inc.; San Jose (CA); On-site; USD 210,000 - 320,000; Full time

Job summary

Adobe Inc. is seeking a Principal Machine Learning Engineer to define the technical architecture of the Agent Harness and lead Adobe’s senior engineers in agentic systems.

You will set long-term direction, solve complex design challenges, and establish standards for AI-native software at scale. You will work with architects across teams to shape agent execution, tool use, context management, and lifecycle orchestration while balancing performance and cost.

Qualifications

• 15+ years of software engineering with demonstrated impact.
• Deep expertise in distributed systems, runtime build, and platform architecture.
• Experience leading large multi-functional initiatives across organizations.
• Hands-on experience fine-tuning, optimizing, and operating models or runtimes at scale.

Responsibilities

• Shape technical direction of Agent Harness and agentic systems.
• Define harness interfaces and standards balancing performance, cost, and reliability.
• Evaluate and adopt AI runtimes and tool-use standards across Adobe.
• Define AI-first architecture and engineering standards for agentic systems.
• Lead cross-team technical initiatives and mentor senior engineers.

Skills

Distributed systems

LLM infrastructure

AI-first architecture

Architectural leadership

Cross-team collaboration

Job description

Adobe Unified Platform is building the system that changes how software gets made at Adobe. A platform that understands builders' intent, breaks down complex work, executes it through autonomous agents, and improves with every cycle. What this team ships multiplies across thousands of Adobe engineers, and it's the substrate the rest of Adobe's agentic efforts build on.

Meta Factory is the core of that platform: the Agentic Builders Experience that defines how agents understand their goals, decompose work, use tools, evaluate their own outcomes, and improve over time. Think of it as our own version of Claude Code, optimized for Adobe needs, model independent and operated for the whole company.

We are looking for a Principal Machine Learning Engineer to define the technical architecture of the Agent Harness and serve as one of Adobe's senior technical leaders in agentic systems. You will set the long-term technical direction, solve the hardest design challenges, and establish engineering standards for AI-native software development at Adobe scale.

What you'll do

• Work as part of a team of architects shaping the technical direction of the Agent Harness, contributing across agent execution, tool use, context, state, and lifecycle management.
• Define harness interfaces and standards while balancing performance, cost, and reliability.
• Track emerging trends in agent runtimes and tool-use standards and lead their evaluation and adoption at Adobe.
• Define AI-first architecture and engineering standards for agentic systems across Adobe.
• Lead cross-team technical initiatives and provide guidance on complex architectural challenges.
• Advise engineering leadership on emerging agentic execution challenges and mentor senior technical talent across the organization.

What you'll need to succeed

• 15+ years of software engineering experience, with a strong record of innovation and business impact at Adobe or across the industry.
• Deep expertise in distributed systems, runtime build, and platform architecture, with experience leading large multi-functional initiatives.
• Recognized expertise in agentic systems and LLM infrastructure, with hands-on experience fine-tuning, optimizing, and operating models or runtimes at scale.
• Experience driving AI-first architecture, engineering standards, technology choices, and product direction across organizations.
• Strong communication and influence skills, with the ability to align senior leaders and teams around a shared technical vision.

Adobe is proud to be an Equal Employment Opportunity employer. We do not discriminate based on gender, race or color, ethnicity or national origin, age, disability, religion, sexual orientation, gender identity or expression, veteran status, or any other protected characteristic. Learn more.