AI Automation Engineer (Claude Code)

Job Description

About You

You are an AI Engineer who turns Claude Code into reliable, unattended automation for real engineering teams. You will join the software team of a channel incentive platform company to adapt an existing Jira support triage routine, built in Claude Code for another product, to a platform of about 70 Node.js and .NET microservices. You will own the work from discovery to handover. You will partner with a subject matter expert from the platform team and present design alternatives to the client’s architect for decision. You are persistent and self-directed, and you are comfortable refining a procedure again and again until the output is right.

Note: This position operates under a contractor framework for an initial period of 3 months and requires availability to work on U.S. Eastern Time (ET), starting at 8:00 AM.

You Bring to Applaudo the Following Competencies:

• Bachelor’s Degree in Computer Science, Software Engineering, Computer Engineering, or a related field is desired, or equivalent professional experience.
• 5+ years of professional software development experience, including production C# and .NET code and reading older .NET Framework code.
• 1+ year of hands-on experience building LLM agents or automations.
• Proven delivery of Claude skills or Claude Code automations used by a real team.
• Experience designing agents through a written procedure, including hard rules, investigation steps, classification logic, and output formats.
• Experience applying least-privilege design to agents, with limits enforced in the environment and permissions.
• Experience running scheduled or unattended agents through Claude Code routines or an equivalent scheduler, including cloud environments and connectors or MCP servers.
• Hands-on experience with Jira Service Management, including JQL, saved filters, boards, the service desk REST API, and the difference between internal and customer-visible comments.
• Experience with GitHub workflows, including apps, branches, draft pull requests, and code review.
• Ability to read and write production C# and .NET code, and to read older .NET Framework code.
• Ability to read Node.js code well enough to trace a feature across microservices.
• SQL skills to read a schema and write scripts that use only existing tables and columns.
• Experience improving prompts from failures by reading session transcripts, finding the root cause of a wrong output, and changing the procedure.
• Ability to learn a large codebase and a support process on your own, with limited time from subject matter experts.
• Sound judgment with customer-facing risk, defaulting to internal communication when a public action cannot be undone.
• Comfort proposing options with clear trade-offs and accepting the architect’s final decision.
• Ability to teach developers who use Claude but have never built a routine.
• Advanced English Proficiency. Strong verbal and written communication skills, including technical discussions, stakeholder interactions, and documentation.

Nice to haves:

• Experience with agent observability, evaluation, or reliability tools.
• MCP server development experience.
• Experience with support operations or IT service management processes.
• Node.js development experience.
• Experience with channel incentive, rebate, or other financial-flow platforms.
• Anthropic, AWS, or other AI certifications/

You Will Be Accountable for the Following Responsibilities:

• Run a one-week discovery of the reference routine and its documented gotchas, the support queue (board, saved filter, statuses, and ticket types), and the repositories and code paths the routine must read.
• Propose the adapted design, covering JQL scope, classification rules, investigation depth, SQL and schema rules, internal and public comment rules, and permissions, and present alternatives to the client’s approver for decision.
• Build the routine by writing the prompt as a numbered procedure with hard rules, configuring the cloud environment, connectors, and schedule, and keeping the prompt in source control.
• Test the routine by hand on one or two tickets, review every comment it posts during the trial, and adjust the prompt for each class of mistake, keeping a dated record of every change.
• Open draft pull requests only through the routine, writing C# code when needed and following the team’s standard review and test process.
• Train the platform engineers on how the routine works, what its labels mean, how to read a session transcript, and how to edit the prompt safely.
• Write the maintenance guide and hand over ownership of the routine to a named owner on the platform team.

Additional Information

All your information will be kept confidential according to EEO guidelines.

About Us

We Are Engineered Different.

At Applaudo, talented people design, build, and scale meaningful, AI-powered solutions that create real business impact. As an AI-native organization, we collaborate across design, development, cloud, data, and artificial intelligence to turn ideas into scalable products that transform how companies operate, make decisions, and grow.

We are building a high-performance culture grounded in five values: Empowering Excellence, Collaborative Teamwork, Unsolicited Respect, Consistent Transparency, and Efficient Communication . These define how we work, how we support one another, and how we hold ourselves accountable.

Applaudo is a place for people who want to learn fast, take ownership, and work alongside strong teams they are proud to belong to. Joining us means being part of an organization that is evolving intentionally, investing in modern ways of working, and leading AI-native transformation at scale.