Software Development Engineer

AI Assistant Agent Architect

Define and evolve agentic architectures for real-world, production workflows. Develop and expand sub-agents within the Adobe Express AI Assistant ecosystem. Define success metrics, guardrails, and acceptance criteria for AI systems. Take ideas from prototype to production; iterate quickly and harden for scale. Balance quick testing with developing scalable, reliable systems. Own key business metrics (quality, adoption, latency, cost), not just feature delivery. Continuously improve agents by analyzing production data to uncover patterns, establishing evaluation pipelines, refining test sets, and running A/B experiments. Identify drift, degradation, and failure modes; drive fixes and improvements.

Strong hands-on experience with LLM APIs (OpenAI, Anthropic, etc.), including tool calling and structured outputs. Solid prompt engineering skills, including advanced prompting and optimization techniques. Experience crafting agent memory, context handling, and state management. Practical experience with RAG pipelines, embeddings, and vector databases. Ability to use AI coding assistants (Claude Code, Cursor, Codex, etc.) as true copilots to build and ship features end-to-end. Experience building and deploying conversational agents or AI workflows in production. Familiarity with AWS or Azure and deploying scalable services. Ability to evaluate and optimize systems across quality, latency, and cost.

5+ years of software engineering experience with strong systems thinking. Proficiency in Python, TypeScript, or similar. Strong understanding of APIs, backend systems, and distributed architectures. Experience with observability (logging, metrics, tracing) to debug and monitor production systems. Experience evaluating performance trade-offs (latency, cost, reliability). Solid foundation in algorithms, data structures, and software building principles. Excellent problem-solving abilities and attention to detail.

Experience with multi-agent systems or orchestration frameworks (LangGraph, CrewAI, AutoGen, etc.). Experience decomposing workflows across agents and managing agent-to-agent communication. Experience crafting eval systems, measuring agent quality, and catching regressions. Familiarity with synthetic data generation and evaluation datasets. Has built and shipped an AI system end-to-end. Comfortable making architecture decisions with incomplete information. Has debugged LLM issues in production (latency, cost, failures, scaling limits). Balances fast delivery with developing scalable, stable systems.

Adobe empowers everyone to create through innovative platforms and tools that unleash creativity, productivity and personalized customer experiences. Adobe's industry-leading offerings including Adobe Acrobat Studio, Adobe Express, Adobe Firefly, Creative Cloud, Adobe Experience Platform, Adobe Experience Manager, and GenStudio enable people and businesses to turn ideas into impact, powered by AI and driven by human ingenuity.

Our 30,000+ employees worldwide are creating the future and raising the bar as we drive the next decade of growth. We're on a mission to hire the very best and believe in creating a company culture where all employees are empowered to make an impact. At Adobe, we believe that great ideas can come from anywhere in the organization. The next big idea could be yours.

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.

Adobe aims to make our Careers website and recruiting process accessible to any and all users. If you have a disability or special need that requires accommodation to navigate our website or complete the application process, email accommodations@adobe.com or call +1 408-536-3015.