Staff Developer, AI Experience

Dayforce

9d•$161,000 - $287,500•Remote

About The Position

Dayforce is building an AI Developer Experience team within Engineering to scale high-quality, agentic development practices across the organization. This team transforms early-stage experimentation into durable, reusable engineering capabilities that development teams can adopt in real codebases under real delivery pressure. The Staff Developer, AI Experience is a senior hands-on engineering role and a key contributor to the broader AI Engineering strategy. This role focuses on building the systems, standards, workflows, and reusable development capabilities that enable engineers to work more effectively with AI-assisted and agentic coding tools. The role combines architectural thinking with hands-on implementation, helping define scalable engineering patterns while working directly within repositories and delivery environments to operationalize modern AI-driven development practices.

Requirements

Strong software engineering background with experience delivering and operating complex production systems.
Hands-on experience using agentic coding tools and AI-assisted development workflows on real engineering problems.
Experience implementing developer workflows across repositories, testing frameworks, CI/CD pipelines, and delivery processes.
Experience with context engineering including prompts, retrieval strategies, memory/state patterns, and LLM tooling configurations.
Experience designing reusable agent skills with defined contracts, evaluation coverage, and operational safeguards.
Demonstrated ability to define engineering standards, guardrails, and evaluation frameworks that improve consistency and quality across teams.
Experience partnering directly with development teams to implement shared engineering practices.
Strong technical judgment distinguishing scalable engineering practices from experimental concepts.
Experience working across organizational boundaries to improve engineering effectiveness and implementation consistency.
Excellent written communication skills with the ability to translate emerging technical practices into actionable engineering guidance.

Nice To Haves

Experience building AI engineering enablement programs at scale.
Strong understanding of LLM evaluation methodologies and operational reliability patterns.
Experience designing enterprise AI developer platforms or reusable internal tooling ecosystems.
Demonstrated ability to influence engineering standards and adoption across large organizations.
Strong understanding of balancing experimentation, governance, scalability, and developer productivity in AI-assisted engineering environments.

Responsibilities

Own and evolve reusable skill design patterns and coding artifact standards that drive AI-assisted development effectiveness across Engineering.
Define how agent context is structured, scoped, and maintained across repositories, toolchains, and delivery pipelines.
Design reusable context patterns including prompts, retrieval strategies, memory/state patterns, and tool exposure configurations.
Establish practical guardrails and standards that reduce failure modes and support responsible AI-assisted development adoption.
Build and maintain reusable AI agent skills, workflows, templates, scaffolding, and implementation guides.
Define production-readiness standards for reusable skills including contracts, triggers, evaluation coverage, failure handling, and documentation.
Partner directly with development teams to operationalize AI-assisted workflows in repositories, testing practices, and engineering delivery processes.
Establish standards for emerging engineering artifacts such as AI-assisted specifications, implementation plans, and workflow patterns.
Define evaluation and adoption criteria for scalable AI engineering capabilities including reliability, engineering value, and maintainability.
Build data-driven visibility into AI-assisted development outcomes and ROI across Engineering.
Define scalable implementation standards that support consistent and lightweight AI engineering adoption.
Partner with internal platform teams and external vendors on tooling integration, feedback, and capability evolution.
Help establish and evolve the AI Engineering enablement operating model including priorities, success metrics, and organizational scaling strategies.