Software Engineer, Feedback & Learning Systems — Meta Factory

Adobe; San Jose (CA); On-site; USD 177,900 - 257,550; Full time

Job summary

Adobe is seeking a Software Engineer for Meta Factory to own key components of the Agent Harness and agent execution systems.

You will implement learning and feedback pipelines, applying RLHF and reward modelling to improve agents across releases, and integrate with evaluation and skills layers.

Qualifications

• 8+ years of software engineering experience delivering AI/data-intensive systems.
• Hands-on experience with LLMs and agentic systems including tool use and feedback-driven improvement.
• Ability to navigate ambiguous technical areas and turn 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 and ML tooling.

Responsibilities

• Build Meta Factory’s agent learning and feedback systems, including evaluation of outputs and improvement loops.
• Develop feedback pipelines to capture agent outcomes and drive system improvements.
• Apply AI-first techniques like RLHF, preference learning, and reward modeling to raise agent quality across releases.
• Define how learning connects with the Agent Harness, evaluation infra, and execution loop.
• Write development docs, review code, and mentor engineers building AI systems.

Skills

AI/ML systems

Python programming

Ambiguity handling

Engineering leadership

Research and evaluation

Tools

Java

Cloud platforms

Job description

Opportunity

Adobe Unified Platform is building the system that changes how software gets made. Meta Factory is the core, providing the Agentic Builders Experience that defines how agents understand goals, decompose work, use tools, evaluate outcomes, and improve over time. 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.

Responsibilities

• 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 release over release.
• Define how the learning layer connects with the Agent Harness, evaluation infrastructure, skills layer, and execution loop.
• Write clear development documentation, review code, and mentor engineers inventing AI systems that learn from user input.

Qualifications

• 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.

Pay

U.S. pay range: $139,000 – $257,550 annually. In California, the range is $177,900 – $257,550.

Equal Employment Opportunity

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.