Enterprise AI Architect

Exadel•Town of Poland, NY

17h

About The Position

Exadel is seeking an experienced Enterprise AI Architect to serve as a Forward Deployed Engineer. The role designs and builds reusable skills for Claude Code, working closely with business stakeholders and domain experts to translate requirements, reference materials, and operational knowledge into reliable capabilities. This hands-on engineering role sits at the intersection of software development, prompt and context engineering, and business process automation. It also provides technical leadership to other engineers through reviews, direction, and unblocking.

Requirements

Strong hands-on experience using Claude Code in real software-development or business-workflow scenarios.
Practical experience creating Claude Code Skills or comparable reusable capabilities for AI coding agents.
Strong understanding of modern AI engineering patterns, including agentic workflows, tool use, prompt engineering, context engineering, and structured instruction design.
Proven hands-on software engineering experience and ability to build, review, test, and maintain production-quality solutions.
Ability to transform business requirements and domain knowledge into clear technical designs and executable workflows.
Experience evaluating and improving non-deterministic AI solutions.
Ability to own the technical shape of the whole capability, including standards, shared components, evaluation and release strategy, and backwards compatibility.
Ability to define and enforce what constitutes a well-formed skill, what belongs in shared infrastructure, and what should be rejected in review.
Ability to make and justify platform-level decisions, including choices about agent harnesses, integration architecture, and build-versus-adopt strategies, with clear technical rationale for foundational decisions affecting the platform.
Professional proficiency or fluency in English.

Nice To Haves

Hands-on experience with Claude Code, particularly authoring Claude Code Skills, plugins, or MCP servers.
Experience with LLM evaluation tooling such as promptfoo, LangSmith, or custom harnesses.
Consulting or professional services background.
Exposure to HR technology, compensation and benefits, payroll, or workforce analytics.
Experience building internal developer tooling or establishing a platform capability.
Public artifacts such as open-source agent tooling, published skills or plugins, conference talks, or technical writing on agentic engineering.

Responsibilities

Collaborate with business stakeholders and domain experts to understand their objectives, processes, constraints, and expected outcomes.
Analyze business requirements, documentation, examples, templates, and other reference materials supplied by stakeholders.
Identify workflows and use cases that can be implemented or improved through Claude Code Skills.
Design, implement, test, and maintain reusable Claude Code Skills.
Create skill instructions, supporting scripts, reference materials, validation logic, and reusable workflow components.
Translate complex or ambiguous business processes into structured, executable instructions for AI agents.
Evaluate skill behavior using realistic scenarios, test cases, and acceptance criteria.
Improve the reliability, accuracy, usability, and maintainability of skills through iterative testing and stakeholder feedback.
Provide technical leadership to other engineers through reviews, direction, and unblocking.