Senior AI Platform Engineer

Adobe Adobe · Enterprise · San Jose, CA +1

Senior engineer to design and build next-generation AI systems for Adobe Express, focusing on scalable, production-grade AI platforms with agentic experiences. This role involves architecting end-to-end systems for model orchestration, tool integration, memory, inference, data flows, and evaluation.

What you'd actually do

  1. 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.
  2. Architect and evolve the AI platform powering Adobe Engineering — with a strong emphasis on Agentic AI systems and LLM-native architectures.
  3. Design and implement scalable orchestration layers that coordinate LLMs, tools, APIs, memory stores, and multi-step reasoning workflows.
  4. Build production-grade agent frameworks that support planning, task decomposition, tool invocation, multi-agent collaboration, and persistent memory.
  5. Develop high-performance inference and runtime systems with strong guarantees around latency, reliability, observability, and cost efficiency.

Skills

Required

  • TypeScript
  • Python
  • systems language (Java, Go, C++)
  • building production AI services
  • large-scale distributed systems
  • AI platforms
  • intelligent service architectures
  • LLM orchestration frameworks
  • model routing strategies
  • multi-model pipelines
  • agentic systems
  • reasoning loops
  • memory persistence
  • tool integration
  • state management
  • multi-agent coordination
  • scalable, cloud-native, microservices-based architectures
  • observability
  • reliability
  • evaluation systems for generative AI quality, task completion, and behavioral robustness

Nice to have

  • architecting AI assistants, copilots, or agent platforms in production environments
  • multimodal generative systems (text, image, video, motion)
  • tool-augmented LLM systems
  • RAG architectures
  • vector databases
  • contextual memory systems
  • evaluation frameworks for generative AI quality and safety
  • contributing to open-source AI frameworks
  • publishing technical thought leadership

What the JD emphasized

  • 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.
  • Hands-on experience designing agentic systems — including reasoning loops, memory persistence, tool integration, state management, and multi-agent coordination.
  • Experience designing evaluation systems for generative AI quality, task completion, and behavioral robustness.

Other signals

  • building scalable Agentic AI platforms
  • LLM-native architectures
  • orchestration layers
  • production-grade agent frameworks
  • high-performance inference and runtime systems
  • evaluation and feedback systems
  • integrating foundation models
  • contextual memory systems