Sr. Staff Software Engineer, Agentic Applications

Databricks•Mountain View, CA

1d•Onsite

About The Position

As a Senior Staff Software Engineer on the Agentic Applications team, you will be the hands-on technical lead for Databricks’ quote-to-cash processes. You will build first-party, agents-first applications on the Databricks Data Intelligence Platform and own technical architecture end to end. The role focuses on designing reliable agents for revenue-critical workflows, setting engineering standards, and ensuring agent-assisted decisions are observable, auditable, and trusted by Finance, Deal Desk, and Sales. This is a hands-on technical leadership role, not a people-management role; you will write code, review designs, and provide senior technical direction. You will define the target architecture across Configure-Price-Quote, deal management, ordering, subscriptions, investments, billing, and revenue recognition, and lead the transition from vendor-configured workflows to first-party, AI-native applications. You will build and evaluate agents for deal guidance, quoting, proposals, approvals, and pricing recommendations; establish human review and approval controls; and provide agents with governed access to business systems and data. The position also protects financial integrity across downstream validation, billing, invoicing, and revenue recognition; plans migration from the existing quoting platform; establishes agent engineering patterns; mentors engineers; and partners with Finance, Deal Desk, Sales Ops, Legal, and Platform Engineering to turn commercial processes into technical roadmaps and measurable outcomes.

Requirements

12+ years of software engineering experience, with a track record of technical leadership and ownership of large-scale production systems.
3+ years of hands-on experience building and operating production LLM-powered or agentic applications, such as agents, RAG pipelines, tool use, or multi-agent orchestration, and evaluation frameworks for generative outputs.
Strong backend and distributed-systems skills, including API and service design, data modeling, idempotency, consistency, transactional integrity, and observability.
Proven experience designing human-in-the-loop systems, including approval workflows, review interfaces, audit trails, and guardrails for probabilistic systems in regulated or high-stakes domains.
Experience leading technical architecture for complex business domains; Quote-to-Cash, Order-to-Revenue, billing, pricing, or other revenue-critical enterprise systems are relevant.
Full-stack fluency across modern web frameworks such as React/TypeScript, backend services using Python, Java, Scala, or Go, and data platforms.
Ability to work directly with non-engineering stakeholders and translate ambiguous business workflows into clear agent and system architecture.
Experience mentoring engineers and improving a team’s technical execution without relying on positional authority.

Nice To Haves

Domain experience with CPQ, deal management, subscription management, or revenue recognition in a high-growth SaaS or consumption-based business.
Experience building first-party applications on enterprise SaaS platforms or replacing them, such as Salesforce CPQ/Revenue Cloud, NetSuite, or Zuora.
Platform-specific configuration expertise.
Experience with the Databricks platform, including Databricks Apps, Lakebase, Unity Catalog, Mosaic AI Agent Framework, or MLflow tracing and evaluation.
Familiarity with SOX controls, audit requirements, and financial-systems compliance.

Responsibilities

Own the agentic architecture for Quote-to-Cash across Configure-Price-Quote, deal management, ordering, subscriptions, investments, billing, and revenue recognition.
Lead the transition from vendor-configured workflows to first-party, AI-native applications built on Databricks Apps, Lakebase, Unity Catalog, and Mosaic AI.
Design and ship LLM-powered agents for deal guidance, quote generation and summarization, multi-option proposals, approval insights, and pricing and discount recommendations.
Work with Sales, Deal Desk, and Finance to define success criteria for agent-assisted workflows.
Own the domain’s agent evaluation and quality system, including workflow quality criteria, offline evaluation suites, LLM-as-judge and human-labeled benchmarks, behavioral regression testing, online tracing, and user feedback loops.
Design human-in-the-loop controls, including separation of agent proposals from committed actions, diff-based review, approval routing, audit logging, and policy guardrails.
Architect tool-calling and MCP-style interfaces that give agents governed, runtime access to pricing, product catalog, order, contract, subscription, and billing data.
Maintain single-source-of-truth principles across CRM, ERP, and billing systems.
Ensure agent-assisted quoting and ordering produce accurate, compliance-grade downstream outputs for order validation, billing, invoicing, and revenue recognition.
Plan and sequence migration from the current production quoting platform to the target architecture, deciding what to retire, rebuild, or wrap while avoiding business disruption.
Lead architecture reviews and establish agent design patterns for orchestration, memory, retrieval, tool use, and multi-agent coordination.
Mentor senior and mid-level engineers in production-grade agentic engineering.
Partner with Finance, Deal Desk, Sales Ops, Legal, and Platform Engineering to translate commercial processes into technical roadmaps and measurable business outcomes.
Write code, review designs, and provide technical leadership without serving as a people manager.