You will move beyond prompt engineering to build production-oriented AI systems that can perform appropriate tasks autonomously, interact with approved tools, analyze structured and unstructured data, and collaborate effectively with human decision-makers.
-
Design and build production-ready AI agents and automation solutions using Anthropic Claude, Claude APIs, Claude Code, Claude Agent SDK, Claude Skills, and related agentic AI technologies.
-
Develop reusable Claude Skills and agent-based automation workflows that support scalable, repeatable enterprise use cases.
-
Integrate AI solutions with approved tools, databases, APIs, enterprise platforms, and workflow orchestration environments.
-
Build secure Model Context Protocol integrations, including custom MCP servers and secure tool connections where required.
-
Translate ambiguous business problems into structured technical requirements, solution designs, measurable outcomes, and maintainable implementation plans.
-
Develop Python-based automation, APIs, asynchronous workflows, data-processing pipelines, and tested software components.
-
Analyze structured and unstructured data to identify automation opportunities, validate solution performance, and measure operational impact.
-
Implement evaluation frameworks, monitoring practices, AI safety controls, security considerations, and production governance for AI-powered systems.
-
Partner with business stakeholders, technology teams, and human decision-makers to ensure AI solutions deliver reliable, measurable value.
-
Provide technical leadership across AI agent architecture, workflow automation, enterprise integration, and evidence-based solution evaluation.
-
Demonstrate end-to-end ownership by moving from unclear business challenges to dependable AI-enabled workflows that improve efficiency, quality, reliability, or cost.
-
Complete all assigned, mandatory training within the timeframe provided.
-
Conduct and/or participate in regularly scheduled 1:1 meetings with your direct manager and/or direct reports.
-
Strong hands-on experience with Python, APIs, asynchronous programming, testing, and modern software engineering practices.
-
Practical experience developing LLM-powered applications, AI agents, or agentic workflows.
-
Working knowledge of Anthropic Claude models, Claude APIs, tool use, and structured output patterns.
-
Ability to design reusable Claude Skills and agent-based automation workflows.
-
Experience integrating applications with databases, external services, APIs, and enterprise platforms.
-
Proficiency with SQL, JSON, YAML, Git, and data-processing libraries.
-
Familiarity with MCP architecture and secure tool integration.
-
Understanding of evaluation frameworks, AI safety, security, monitoring, and production deployment practices.
-
Demonstrated ability to translate ambiguous requirements into maintainable, reliable technical solutions.
-
Production experience with Claude Code, Claude Agent SDK, and custom MCP servers is preferred.
-
Experience implementing multi-agent orchestration and agent evaluation frameworks is preferred.
-
Experience with FastAPI, Pydantic, pandas, pytest, Docker, and CI/CD is preferred.
-
Experience integrating Jira, Confluence, GitHub, Microsoft 365, or similar enterprise platforms is preferred.
-
Knowledge of retrieval-augmented generation, vector databases, semantic search, and knowledge engineering is preferred.
-
Familiarity with cloud infrastructure such as AWS, Azure, or Google Cloud is preferred.
-
Experience with enterprise automation platforms such as n8n, Airflow, or equivalent solutions is preferred.
-
Demonstrated experience measuring automation ROI and operational improvements is preferred.
-
Ability to show practical delivery experience through working Claude agents, reusable Claude Skills, secure MCP integrations, well-engineered Python automation, and evidence-based evaluation.
