AI Feedback & Learning Systems Engineer

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

Job summary

Adobe Unified Platform is building a cutting‑edge system for agent execution and learning. We seek a Software Engineer with deep hands‑on experience in agent execution, tool calling, context and state management, and sandboxed runtimes to own key components of Meta Factory's Agent Harness.

You will implement learning and feedback loops, apply RLHF and reward modeling, and mentor peers while collaborating with engineering and platform teams to ship robust AI systems that improve with user

Qualifications

• 8+ years of software engineering experience with AI/data‑intensive systems.
• Hands‑on with LLM and agentic systems, including evaluation and RLHF.
• Able to turn ambiguous technical goals into working systems.
• Experience applying AI to real products with measurable impact.
• Proficient in Python and at least one other language.
• Experience with cloud platforms (AWS/Azure), data pipeline tools, and ML experimentation infrastructure.

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 docs, review code, and mentor engineers inventing AI systems that learn from user input.

Skills

LLM & agentic systems

Tool use & context management

RLHF / reward modeling

Python & another language

Cloud platforms (AWS/Azure)

Tools

AWS

Azure

Data pipelines tools

ML experimentation infra

Job description

Adobe Unified Platform is building a cutting‑edge system for agent execution and learning. We seek a Software Engineer with deep hands‑on experience in agent execution, tool calling, context and state management, and sandboxed runtimes to own key components of Meta Factory's Agent Harness.

You will implement learning and feedback loops, apply RLHF and reward modeling, and mentor peers while collaborating with engineering and platform teams to ship robust AI systems that improve with user