Principal AI Systems Engineer- Agentic and Productivity Systems

Senior AI Systems Engineer

The Creative Cloud Engineering organization is building the next generation of AI-powered engineering infrastructure to accelerate developer productivity and operational excellence across the Creative Cloud ecosystem. As we expand into AI-driven workflows across developer productivity and platform initiatives, we are looking for a Senior AI Systems Engineer who operates at the intersection of experimentation and production systems. This role focuses on designing, orchestrating, and operationalizing agent-based systems that improve engineering workflows across CI/CD, developer tooling, and operational diagnostics.

This is not a research role and not a prompt-engineering role. This is a systems engineering role focused on building durable infrastructure. You will help build AI-native engineering capabilities that compound engineering velocity across Creative Cloud over time.

Agentic Workflow Development

· Design and prototype agent-based systems for engineering workflows such as CI diagnostics, code review automation, build failure triage, and autonomous debugging

· Develop multi-agent orchestration patterns with structured state, memory, and control boundaries

· Rapidly evaluate emerging AI frameworks, agent tooling, and developer AI platforms in real-world engineering environments

AI Systems Infrastructure

· Build reusable orchestration layers and service architectures for AI-powered engineering systems

· Develop structured evaluation pipelines including trace-based evaluation and regression testing for agent behavior

· Implement feedback loops and instrumentation that continuously improve AI system performance

Production Hardening

· Convert experimental workflows into secure, scalable, production-grade services

· Implement observability, tracing, cost controls, and model routing

· Ensure reliability, operational stability, and measurable impact of AI-powered systems

Platform Strategy & Collaboration

· Define internal standards for AI experimentation, evaluation, deployment, and monitoring

· Partner with Dev Ex, CI/CD, and platform teams across Creative Cloud to embed AI-native capabilities

· Build cohesive infrastructure that prevents tool sprawl and enables reusable AI productivity systems across teams

What Success Looks Like

· Production-grade AI agents integrated into engineering workflows and CI systems

· A standardized evaluation and tracing framework adopted across Creative Cloud engineering teams

· Measurable reductions in manual debugging, failure triage, and operational friction

· Reusable AI infrastructure components leveraged across multiple engineering teams

· A clear AI productivity roadmap aligned with Creative Cloud platform initiatives

Required Qualifications

· 8+ years of software engineering experience, with demonstrated depth in systems-level work

· Strong systems engineering experience (Python, Go, Type Script, or similar)

· Experience building distributed systems, developer platforms, or infrastructure services

· Experience integrating LLMs or AI APIs into production systems

· Experience evaluating and integrating across multiple AI providers (e.g., AWS Bedrock, Anthropic, OpenAI) including cost optimization and capacity planning

· Strong understanding of observability, metrics, logging, and tracing systems

· Experience operating production services at scale

Preferred Qualifications

· Experience with agent frameworks (Lang Graph, Auto Gen, CrewAI, or similar)

· Experience with embeddings, vector databases, or RAG architectures

· Experience designing evaluation and benchmarking systems for AI workflows

· Experience with CI/CD platforms, developer tooling, or build systems

· Experience building internal developer productivity platforms

· Familiarity with cost-aware model orchestration and multi-model routing

Ideal Candidate Profile

· Has built and shipped an AI-powered system end-to-end, not just integrated an API

· Can show a prototype they took from experiment to production

· Comfortable making infrastructure decisions with incomplete information

· Has debugged LLM reliability issues in production (latency, cost, failure modes, concurrency limits)

· Experimental but pragmatic —…