Enterprise AI Architect

Description

The company is an AI-first global technology firm with more than 25 years of engineering leadership, over 2,000 team members, and more than 500 live projects for Fortune 500 clients, including HBO, Microsoft, Google, and Starbucks.

Its work runs from AI platforms to digital transformation, with enterprise leaders as partners.

The client is the largest human resources consulting firm in the world, based in New York City, with main branches in 40+ countries, over 25,000 employees, and operations in more than 130 countries. Its services are used by 97% of Fortune 500 companies.

This role is for an Enterprise AI Architect working as a Forward Deployed Engineer. You will design and build reusable Claude Code Skills, working alongside business stakeholders and domain experts to turn their requirements, reference material, and operational know-how into dependable skills.

It is hands-on engineering that combines software development, prompt and context engineering, and automation of business processes.

Responsibilities

• Lead the other engineers through code review, technical direction, and clearing blockers.
• Design, build, test, and maintain reusable Claude Code Skills.
• Find workflows that Claude Code Skills could implement or improve.
• Work with stakeholders and domain experts to learn their goals, processes, limits, and expected results.
• Review the documents, examples, templates, and other materials stakeholders provide.
• Turn messy or unclear business processes into structured steps an AI agent can carry out.
• Write skill instructions, helper scripts, reference material, validation logic, and reusable workflow parts.
• Test skills against realistic scenarios, test cases, and acceptance criteria.
• Make skills more reliable, accurate, usable, and easier to maintain through repeated testing and stakeholder feedback.

Requirements

• Solid hands-on experience with Claude Code in software development or business workflows.
• Hands-on experience authoring Claude Code Skills, plugins, or MCP servers.
• Practical experience building Claude Code Skills or similar reusable capabilities for AI coding agents.
• Good grasp of AI engineering patterns such as agentic workflows, tool use, prompt engineering, context engineering, and structured instruction design.
• Proven software engineering skills: you can build, review, test, and maintain production-quality solutions.
• Able to turn business requirements and domain knowledge into clear technical designs and executable workflows.
• Experience evaluating and improving non-deterministic AI solutions, with evaluation tooling for LLM systems such as promptfoo, LangSmith, or custom harnesses.
• Able to own the technical shape of the whole capability rather than individual skills, covering standards, shared components, evaluation and release strategy, and backward compatibility.
• Able to define and enforce what a well-formed skill looks like, what belongs in shared infrastructure, and what review rejects.
• Able to make and defend platform-level decisions, including agent harnesses, integration architecture, and build-versus-adopt choices, with clear technical reasoning for foundational decisions.
• Consulting or professional services background.
• Domain exposure to HR technology, compensation and benefits, payroll, or workforce analytics.
• Experience building internal developer tooling or standing up a platform capability.
• Public work such as open-source agent tooling, published skills or plugins, conference talks, or technical writing on agentic engineering.
• Professional-level or fluent English.