AI Engineer 4
Backend Developer
Agentic Ai
AI
Ai Agent
Ai Agent Platform
Ai Orchestration
Application Security
Artificial Intelligence
Automation
Big Data
Bigdata
Cloud
Cloud Data Engineering
Cloud Data Platform
Cloud Infrastructure
Cloud Native
Cloud Platform
Cloud Platforms
Cloud Platforms Cloud Platforms
Cloud Technology
Data Analysis
Data Analytics
Data Architecture
Data Engineer
Data Engineering
Data Integration
Data Lakehouse
Data Pipeline
Data Pipelines
Data Platform
Data Processing
Data Warehouse
Database
Databases
Databricks
DevOps
DevSecOps
Engineering
Engineering Software
Generative AI
Graph Database
Information Technology (IT)
Infrastructure As Code
Integration
Kafka
Kubernetes
Open Source Ai
Pgvector
Platform Engineering
Programming
Programming Language
Programming Languages
Security Automation
Software Security
Spark
SQL
Streaming Data
Vector Databases
Job Description
Adobe is building autonomous, agentic AI capabilities inside its OneAI platform, with a focus on producing trustworthy answers that cite the underlying sources. In this role, you will design and ship reusable AI components that connect to enterprise data systems, then take them from prototype to production while improving reasoning quality, reliability, and performance.
You will own the work end to end, collaborating across product and data engineering to shape what gets built, and help the team raise the bar through rigorous evaluation.
What you’ll do
- Build and productionize reusable agentic components, including skills, orchestration workflows, and tool-calling integrations that plug into OneAI’s intelligence layer (Neo4j + pgvector + Databricks + Claude).
- Move AI models and agent workflows from prototype to production, and support them to keep performance stable after launch.
- Improve how agents reason through prompt design, memory and context management, retrieval quality, and multi-step tool use.
- Tune for latency, reliability, and cost so the platform scales as more teams depend on it.
- Partner with product managers and data engineers to influence scope and implementation, and share learnings with the broader team.
- Raise evaluation standards by measuring solve rates and accuracy, using results to iterate on agent behavior.
What you bring
- Around 3+ years building AI/ML or backend systems, including experience operating LLM-powered services in production.
- Strong Python fundamentals and experience building with REST APIs.
- Familiarity with modern AI tooling such as LangChain or LlamaIndex, plus experience working with vector databases.
- A measurement-first approach, iterating based on quality signals rather than relying on one-time launches.
- Comfort with cloud platforms (AWS, GCP, or Azure) and containers (Docker, Kubernetes).
Technologies you’ll work with
- OneAI, Neo4j, pgvector, Databricks, Claude
- Python, REST APIs
- LangChain, LlamaIndex, vector databases
- AWS, GCP, Azure
- Docker, Kubernetes
- Kafka, Flink, Kinesis, Spark, CI/CD
- Monitoring, alerting, incident response
Nice to have
- Experience with event streaming (Kafka, Flink, or Kinesis) and data pipelines (Spark or Databricks).
- Exposure to production operations such as CI/CD, monitoring, alerting, and incident response.
- Interest in AI governance, safety, or evaluation.
Location: San Jose, CA (onsite)
Salary range: USD 139,000 - 257,550 per year
Minimum experience: 3 years
Similar Jobs
