The OpportunityAdobe 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 Software Engineer with strong hands-on expertise in agent execution, tool calling, context and state management, and sandboxed runtime systems to build and own key components of Meta Factory's Agent Harness.
What you'll do- Build Meta Factory's agent learning and feedback systems, including how agents evaluate outputs and improve over time.
- Build feedback pipelines that capture agent outcomes, identify quality signals, and turn those signals into system improvements.
- Apply AI-first techniques such as preference learning, reward modeling, reinforcement learning, and evaluation-driven improvement to raise agent quality re`lease over release.
- Define how the learning layer connects with the Agent Harness, evaluation infrastructure, skills layer, and execution loop.
- Write clear development docs, review code, and mentor engineers inventing AI systems that learn from user input.
What you'll need to succeed- 8+ years of software engineering experience, including delivery of complex AI, ML, or data-intensive systems.
- Hands-on experience with LLM and agentic systems, including tool use, context management, output evaluation, and feedback-driven improvement techniques such as RLHF, preference learning, or reward modeling.
- Ability to make progress in ambiguous technical areas and turn broad goals into working systems.
- Experience applying AI techniques to real products or platforms with measurable impact.
- Proficiency in Python and at least one other programming language.
- Experience with cloud platforms such as AWS or Azure, data pipeline tools, and ML experimentation infrastructure.
Expected Pay Range:Our compensation reflects the cost of labor across several U.S. geographic markets, and we pay differently based on those defined markets. The U.S. pay range for this position is $139,000 -- $257,550 annually. Pay within this range varies by work location and may also depend on job-related knowledge, skills, and experience. Your recruiter can share more about the specific salary range for the job location during the hiring process.
In California, the pay range for this position is $177,900 - $257,550
At Adobe, for sales roles starting salaries are expressed as total target compensation (TTC = base + commission), and short-term incentives are in the form of sales commission plans. Non-sales roles starting salaries are expressed as base salary and short-term incentives are in the form of the Annual Incentive Plan (AIP).
In addition, certain roles may be eligible for long-term incentives in the form of a new hire equity award.
