Claude SME

DataDrone Inc.; Cheyenne, Northern (WY, KY); Hybrid; USD 140,000 - 190,000; Full time

Job summary

DataDrone Inc. is seeking a production Claude workflow expert to own the technical design of the end-to-end AI workflow. You will define prompts, agent loops, retrieval, and guardrails to ensure accurate, bounded behavior in production.

You will work with the Integration Engineer to ship in client stacks within 45 days, build eval suites, and establish concrete acceptance criteria so QA can verify readiness to ship.

Qualifications

• Deep experience with Claude or similar LLMs.
• Hands-on prompt engineering and tooling.
• Ability to design safe guardrails and evals.
• Proven track record shipping production AI workflows.

Responsibilities

• Own the technical design of production Claude workflows.
• Engineer prompts, agent patterns, and retrieval.
• Design and configure guardrails for production safety.
• Build eval suites to measure accuracy and quality.
• Collaborate with Integration Engineer to deploy in client stacks.
• Set QA acceptance criteria for ship-ready work.
• Diagnose Claude behavior issues and implement fixes.

Skills

Prompt engineering

Claude API

Guardrails design

Eval frameworks

Production design

Tools

Anthropic Console

Notion

Trello/Jira/Linear

Zoho CRM

Job description

DataDrone runs partner implementation practices that ship one outcome in 45 days. The Anthropic practice gets one production AI workflow live in 45 days on Anthropic's Claude — past the pilot graveyard, into real use. Typical outcome: roughly 80% of a manual process automated and running.

We sell outcomes, never licenses. No shelfware, no drift. We prove the work with screenshots, not poetry — and that means workflows that hold up in production, not demos that fall over. The work is the conversation. No surprises.

What You'll Do

You're the Anthropic and Claude domain expert. You own the technical design of the production AI workflow: how we prompt, where we use agents and tool-use, how we wire the Claude API, what guardrails we set, and how we prove it with evals. You're the person who knows what Claude does well, where it breaks, and how to design around both.

You translate a locked use case into a design that survives production — accurate, bounded, and measurable. You set the eval bar so QA has something concrete to validate against. When the team hits a hard Claude problem, you're the one who solves it.

Daily Rhythm (How You Operate)

You start the day on the active design problems: the prompt that needs tightening, the agent loop that needs bounding, the guardrail that needs to hold. You spend deep blocks designing and testing — prompts, tool-use schemas, retrieval strategy, eval suites — and pairing with the Integration Engineer to get the design into the real stack. You set the accuracy and guardrail bar with QA so "done" is measurable, not a vibe. When Claude behaves in a way the client didn't expect, you diagnose it and design the fix. You close the day with design decisions documented and the eval picture honest. No drift, no hand-waving.

Key Responsibilities

• Own the technical design of the production Claude workflow end to end.


• Engineer prompts, agent/tool-use patterns, and retrieval for accuracy and reliability.


• Design and configure guardrails so the workflow stays bounded and safe in production.


• Build eval suites that make accuracy and quality measurable, not anecdotal.


• Partner with the Integration Engineer to get the design live in the client's stack.


• Set the acceptance bar with QA; define what "good enough to ship" means concretely.


• Diagnose and solve hard Claude behavior problems; document design decisions.

What We're Looking For

• Real depth in prompt engineering — getting reliable, bounded behavior out of Claude or comparable LLMs.


• Hands‑on command of agents and tool-use patterns and the Claude API.


• Proven skill designing guardrails and building evals to measure quality.


• Strong sense for where LLMs break and how to design workflows that hold in production.


• The ability to set a concrete acceptance bar others can validate against.

Bonus Points For

• Direct experience shipping Claude (or comparable LLM) workflows to production, not just prototypes.


• Familiarity with retrieval, context engineering, and structured output patterns.


• Experience defining and running eval frameworks at scale.

The Mindset We Hire For

You design for production, not for the demo. You assume the model will surprise you and you build guardrails and evals so it can't surprise the client. You set a measurable bar because "it looks good" isn't a standard. You'd rather ship one workflow that holds than ten that impress in a sandbox and break in week two.

Success in This Role

• 30 days — You own the technical design of active engagements and have a clear eval and guardrail approach for each.


• 60 days — Your designs are live in real stacks with measurable accuracy, bounded behavior, and evals QA can run.


• 90 days — You've shipped production Claude workflows that hold up, set a repeatable design‑and‑eval pattern for the practice, and become the person the team routes hard Claude problems to.

Tools You'll Use

Claude API and Anthropic Console; prompt and eval frameworks; agent/tool-use and retrieval tooling; the practice's AI Copilot; Notion (design docs, prompt and eval libraries); Trello / Jira / Linear for build tracking; Zoho CRM (read access for client context).

Why Join Us

You do the deep Claude work and you do it where it actually ships — to production, in 45 days, in front of real users. No prototype theater, no shelfware. You set the standard for how the practice designs AI workflows, and you prove it with screenshots, not poetry. The hard problems land on your desk because you're the one who can solve them.

Self-Check Before You Apply

• I can get reliable, bounded behavior out of Claude or a comparable LLM.


• I'm fluent in agents, tool-use, and the Claude API.


• I design guardrails and build evals as a matter of course.


• I know where LLMs break and design workflows that survive production.


• I set a concrete, measurable acceptance bar others can validate.


• I’d rather ship one workflow that holds than ten that only demo well.