AI Prompt Engineer

Matter Intelligence; Remote; EUR 60.000 - 80.000; Teilzeit

Zusammenfassung

A healthcare technology firm is searching for an AI Prompt Engineer to design high-precision prompts and build multi-step LLM workflows. This remote role offers flexible hours and involves debugging outputs, maintaining a versioned prompt library, and contributing to AI strategy. Ideal candidates should have hands-on LLM experience, attention to detail, and the ability to work independently. Join a dynamic team that values your career growth and leverages cutting-edge AI technology to assist patients in healthcare decisions.

Leistungen

Flexible hours

Opportunity to connect with networks of startups

Career growth support

Qualifikationen

• Hands-on experience writing and testing complex prompts for LLMs.
• Understanding of prompt orchestration including templating and variable injection.
• Ability to meet deadlines of a couple of days when necessary.
• Ability to work independently with close collaboration.
• Relentlessly detail-oriented with zero tolerance for silent hallucinations.
• Experience with prompt/eval tooling to evaluate accuracy and tradeoffs.
• Ability to overlap at least 3 hours with U.S. Eastern Time.

Aufgaben

• Design schema-guided prompts for structured extraction over long documents.
• Build modular, multi-step LLM workflows broken into clear stages.
• Debug and improve outputs by analyzing failure modes and implementing solutions.
• Maintain a versioned prompt library and standardize effective approaches.
• Contribute to AI strategy suggesting new frameworks and techniques.

Kenntnisse

Writing and testing complex prompts for LLMs

Understanding of prompt orchestration

Ability to meet deadlines

Ability to work independently

Detail-oriented

Experience with prompt/eval tooling

Ability to overlap with U.S. Eastern Time

Tools

Langfuse

Langflow

Vellum

PromptLayer

Helicone

Jobbeschreibung

Location

Remote

Employment Type

Full time

Location Type

Remote

Department

Paxos

Paxos Health is looking for a part‑time AI Prompt Engineer, likely 10‑15 hours per week. This role is remote-friendly, and the hours are flexible. We are open to expanding this to a full‑time role in the future pending your preferences and business needs as we grow.

We are a fast‑growing company (with venture capital funding) that uses LLMs and AI agents to help medical patients fight their health insurance companies to get covered for life‑saving and life‑changing treatments. Our AI reads all of a patient’s medical documents to come up with the best possible argument about why an upcoming treatment is needed, and then it generates all the paperwork and follows up with the health insurer. We partner with medical device companies so our service is totally free to patients! See our website here.

Job Responsibilities

• Design high‑precision, schema‑guided prompts for structured extraction and complex decision logic over long documents, with careful management of versioned JSON schemas and downstream compatibility.

• Build modular, multi‑step LLM workflows by decomposing complex problems into clearly defined stages, managing intermediate state, and ensuring reliable, production‑ready execution.

• Debug and improve outputs by analyzing failure modes and implementing guardrails such as schema validation and retries, constrained decoding, deterministic tools or retrieval, and rule‑based post‑processing.

• Maintain a versioned prompt library and contribute prompt patterns and best practices, including standardizing approaches that have proven effective via evaluation sets, A/B testing, and quality metrics.

• Contribute to AI strategy: suggest changes to how we orchestrate and use AI to advance our business goals, particularly as we grow. We’re always open to new frameworks and techniques!

Qualifications

Required:

• Hands‑on experience writing and testing complex prompts for LLMs.

• Understanding of prompt orchestration, including templating and variable injection; role design (system/user/tool); few‑shot exemplar selection; structured JSON output enforcement (schemas, validators, retries); and tool‑calling for retrieval and citation (e.g., linking outputs to specific document sections or PDF coordinates).

• Ability to meet deadlines of a couple days when necessary. The hours are flexible, but sometimes we need relatively quick turnaround time for customers.

• Ability to work independently. We will collaborate closely with you, but you should be able to execute on tasks and small projects on your own.

• Relentlessly detail‑oriented, with zero tolerance for silent hallucinations

• Experience with prompt/eval tooling (e.g., Langfuse, Langflow, Vellum, PromptLayer, Helicone), with comfort evaluating per‑criterion accuracy, traceability, and error tradeoffs.

• Ability to overlap at least 3 hours with U.S. Eastern Time standard business hours.

Nice to have:

• Experience using RAG technology for processing long documents.

• Light scripting experience: Able to write small Python or TypeScript scripts to wire prompts into pipelines, run evals end‑to‑end, do basic post‑processing, etc.

• Healthcare industry experience.

Paxos Health is a company founded out of Stanford and backed by leading venture capital firms. The team has engineering and product management backgrounds in the medtech industry (Medtronic) and top technology companies (Meta and Microsoft), as well as founding experience across multiple startups and healthcare nonprofits. Haley and Alex both hold MBAs from Stanford University. Ben, our founding engineer, holds an M. Eng. from Cornell, previously built his own ML startup, and has many years of experience with building innovative software products.

We will help you build skills and connect you with our networks of startups and tech companies, many of whom also want to hire for similar roles. We care deeply about your career growth, and we’ll help you build any skills you need.