The Opportunity

We are seeking a Staff Engineer - AI for Engineering to design and build the next-generation AI systems that bring intelligent, adaptive, and agentic experiences to Adobe Express.

This role is ideal for an engineer who deeply understands how modern LLMs and generative models behave in real-world systems — including reasoning patterns, tool use, prompt dynamics, failure modes, and orchestration strategies — and can translate that understanding into scalable, production-ready platforms.

You will define and build the end-to-end architecture that enables Agentic AI solutions solving real engineering problems— spanning model orchestration, tool integration, memory systems, inference services, data flows, evaluation loops, and real-time decision systems.

This is a systems-first AI role focused on building intelligent platforms.

What You’ll Do

• A core part of this role is building scalable Agentic AI platforms that empower developers, significantly boost engineering productivity, and accelerate AI adoption across the organization.

• Architect and evolve the AI platform powering Adobe Engineering — with a strong emphasis on Agentic AI systems and LLM-native architectures.

• Design and implement scalable orchestration layers that coordinate LLMs, tools, APIs, memory stores, and multi-step reasoning workflows.

• Build production-grade agent frameworks that support planning, task decomposition, tool invocation, multi-agent collaboration, and persistent memory.

• Develop high-performance inference and runtime systems with strong guarantees around latency, reliability, observability, and cost efficiency.

• Design evaluation and feedback systems that measure reasoning quality, task success, hallucination rates, and agent behavior — enabling rapid iteration and continuous improvement.

• Integrate first-party and third-party foundation models into cohesive, adaptive systems using routing, model selection, guardrails, and fallback strategies.

• Design data flows, session-level intelligence, and contextual memory systems that allow agents to operate coherently across interactions.

• Partner with applied research, product, and platform teams to bring intelligent agentic capabilities into real developer-facing experiences.

• Drive architectural strategy for AI for Engineering — connecting models, reasoning engines, tools, and data streams into adaptive AI systems.

• Mentor senior engineers in modern AI system design, LLM orchestration patterns, and agent platform architecture.

What You’ll Bring

• 10+ years of experience building large-scale distributed systems, AI platforms, or intelligent service architectures.

• Deep understanding of how LLMs behave in production environments — including prompting strategies, reasoning chains, tool usage, grounding techniques, hallucination mitigation, guardrails, and evaluation patterns.

• Strong experience building AI-powered systems using LLM orchestration frameworks, model routing strategies, and multi-model pipelines.

• Hands-on experience designing agentic systems — including reasoning loops, memory persistence, tool integration, state management, and multi-agent coordination.

• Proven expertise in building scalable, cloud-native, microservices-based architectures with strong observability and reliability.

• Experience designing evaluation systems for generative AI quality, task completion, and behavioral robustness.

• Proficiency in TypeScript, Python and at least one systems language (Java, Go, C++), with experience building production AI services.

• Strong systems thinking — ability to connect model capabilities, runtime constraints, and product requirements into coherent architectures.

• Excellent multi-functional communication skills, with experience influencing architectural direction across research and engineering teams.

Preferred Qualifications

• Experience architecting AI assistants, copilots, or agent platforms in production environments.

• Experience working with multimodal generative systems (text, image, video, motion).

• Familiarity with tool-augmented LLM systems, RAG architectures, vector databases, and contextual memory systems.

• Exposure to evaluation frameworks for generative AI quality and safety.

• Experience contributing to open-source AI frameworks or publishing technical thought leadership.

AI Use Guidelines for Interviews:
Our interviews are designed to reflect your own skills and thinking. The use of AI or recording tools during live interviews is not permitted unless explicitly invited by the interviewer or approved in advance as part of a reasonable accommodation. If these tools are used inappropriately or in a way that misrepresents your work, your application may not move forward in the process.

At Adobe, we empower employees to innovate with AI — and we look for candidates eager to do the same. As part of the hiring experience, we provide clear guidance on where AI is encouraged during the process and where it’s restricted during live interviews. See how we think about .

Expected Pay Range:

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.