Senior AI Engineer, Production LLM Agents

Adobe; San Jose (CA); On-site; USD 178,000 - 258,000; Full time

Job summary

Adobe in San Jose, CA is seeking an AI/backend engineer to build and productionize reusable agentic components that plug into its intelligence layer. You’ll champion multi-step tool use, improve agent reasoning, and optimize latency, reliability, and cost for scale.

Partner with product managers, data engineers, and ops to ship robust AI services using Python, REST APIs, LangChain/LlamaIndex, and cloud platforms.

Qualifications

• 3+ years building AI/ML or backend systems, with production exposure to LLM-powered services.
• Strong Python and REST API fundamentals.
• Familiar with modern AI tooling (LangChain/LlamaIndex) and vector databases.
• Experience with cloud platforms (AWS/GCP/Azure) and containers (Docker/Kubernetes).
• Nice to have event streaming (Kafka/Flink/Kinesis) and data pipelines (Spark/Databricks).
• Exposure to production operations (CI/CD, monitoring, incident response).
• Interest in AI governance, safety, or evaluation.

Responsibilities

• Build and productionize reusable agentic components (skills, orchestration workflows, tool-calling); integrate into OneAI's intelligence layer.
• Improve agent reasoning: prompt design, memory/context management, retrieval quality, multi-step tool use.
• Tune for latency, reliability, and cost for growing usage across teams.
• Collaborate with product managers and data engineers to shape features; share learnings with the team.
• Measure solve rates and accuracy to elevate agent performance.

Skills

Python

REST APIs

LangChain

LlamaIndex

Cloud platforms

Docker

Kubernetes

Kafka

Spark/Databricks

CI/CD

Tools

AWS

GCP

Azure

Job description

Adobe in San Jose, CA is seeking an AI/backend engineer to build and productionize reusable agentic components that plug into its intelligence layer. You’ll champion multi-step tool use, improve agent reasoning, and optimize latency, reliability, and cost for scale.

Partner with product managers, data engineers, and ops to ship robust AI services using Python, REST APIs, LangChain/LlamaIndex, and cloud platforms.