Staff Software Engineer, Agentic Applications
Databricks · Mountain View, California · Engineering · listed July 15, 2026
The shape of it
Seniority
Staff
Experience asked
12+ years
Where
Not stated
Stated pay
$198,200 – $272,600 USD
Requirements listed
6
Length
836 words
In the posting’s own words
As Staff Software Engineer, Marketing Agents on the Web Engineering team, you will own the architecture and delivery of agents that transform how Databricks creates, publishes, and ships for the web, shifting content operations from a linear, engineering-dependent process to an orchestrated, continuously improving system. You will define how LLM-powered agents participate reliably across marketing content workflows, set the engineering standards the team builds on, and ensure agent output is robust, observable, and production-ready at scale.
What it asks for · 6
- 12+ years of software engineering experience with a clear track record of technical ownership on production systems
- Hands-on experience building and operating LLM-powered systems in production, and a strong instinct for designing quality and evaluation frameworks for probabilistic or generative outputs
- Strong understanding of human in the loop system design: approval workflows, review interfaces, audit logging, and guardrail implementation
- Deep understanding of how agents interact with content systems, publishing pipelines, and web infrastructure including CMS, deployment pipelines, and edge delivery
- Ability to work directly with non-engineering stakeholders to translate workflow requirements into agent architecture
- Experience mentoring engineers and elevating technical execution across a team
What the job covers
- Own the architecture and delivery of agentic workflows that enable marketing to self-serve content creation and publishing across blogs, landing pages, microsites, and social, working directly with marketing stakeholders to understand their workflows, define quality criteria, and build tools they trust and use
- Partner with the Web Platform Staff Engineer on CMS architecture to ensure the content model supports agent read and write workflows and that agent-generated content is structured for AI-driven discovery at production scale
- Build and own the agent reliability system for this domain: define output quality criteria per workflow, implement eval suites and behavioral regression testing, and build feedback loops that improve agent output over time based on what marketers approve, edit, and reject
- Architect human in the loop review as a system property across the full publishing pipeline: proposal and commit separation, diff-based review UI, approval routing, notification system, and audit logging that govern when agents publish autonomously and when human judgment is required
- Encode brand, legal, and compliance constraints as enforceable guardrails within agent workflows, ensuring agents operate within defined boundaries without requiring human intervention on every decision
- Partner with the Web Products Staff Engineer to ensure agent-generated content meets surface quality and brand standards across databricks.com
- Mentor and grow the Senior Engineer on the team, setting the standard for production-grade agentic engineering at Databricks
Tools and skills named
Data
- Databricks3×
Models & research
- LLM2×
Security & compliance
- Audit2×
Ways of working
- Mentorship
- Testing
Words the posting leans on
- agent12×
- system8×
- workflows8×
- content7×
- engineer5×
- web5×
- architecture4×
- build4×
- engineering4×
- human4×
- marketing4×
- output4×
- quality4×
- define3×
- delivery3×
- ensure3×
Counted from the posting after the mission statement and the legal notices are set aside. The ones near the top are the ones a screener is looking for.
The posting, your resume, and the gaps between them. One click loads all three.