Prompt Engineer

Moonfire; Detroit (MI); Remote; USD 130,000 - 180,000; Full time

Benefits offered by this job

Fully remote-friendly within the US

Competitive salary and meaningful

Equity included

Medical, dental and vision covered

401(k) with company match

Unlimited PTO with a 3-week minimum

Learning budget

Home office stipend

Job summary

AIApply is hiring a Prompt Engineer to join our remote team across the United States. You will design, test and maintain prompt systems for resume rewriting, cover letters and interview coaching, treating prompts as versioned production assets.

You will build evaluation loops, benchmark models, reduce hallucinations, tune tone and cost, and document architecture for engineers. Compensation ranges from $130k to $180k plus equity, with full health coverage, a 401(k) match and generous PTO.

Qualifications

• 2+ years hands-on with LLMs in production.
• Strong writing and editorial judgement.
• Comfortable scripting in Python.
• Remote work within US time zones.

Responsibilities

• Design and version prompt systems across product surfaces.
• Build automated and human evaluation loops.
• Benchmark models and recommend the right one per task.
• Reduce hallucination and unsafe output with guardrails.
• Tune for tone, accuracy and cost together.
• Document prompt architecture for engineers.

Skills

Prompt engineering

LLM evaluation

Python

Few-shot design

Guardrails

Model comparison

Data annotation

Content quality

Experimentation

Job description

AIApply is hiring a Prompt Engineer to join our team, fully remote across the United States.

AIApply builds AI tools that help millions of people find work faster: automated job applications, resume optimisation, interview preparation and job matching. We are a small, senior team shipping quickly to a very large audience, and this role has direct impact on whether people get hired.

About the role
You will design, test and maintain the prompt systems behind resume rewriting, cover letters and interview coaching, treating prompts as versioned, evaluated production assets.

• Design and version prompt systems across product surfaces.
• Build automated and human evaluation loops.
• Benchmark models and recommend the right one per task.
• Reduce hallucination and unsafe output with guardrails.
• Tune for tone, accuracy and cost together.
• Document prompt architecture for engineers.

• 2+ years working hands-on with LLMs in production.
• Strong writing and editorial judgement.
• Comfortable scripting in Python.
• Systematic approach to evaluation.
• Curiosity about model behaviour.

Compensation and benefits
The salary range for this role is $130,000 - $180,000 + equity. Final offers depend on experience and location within the United States. All employees receive equity, comprehensive health cover, a 401(k) match, generous paid time off, a learning budget and a home office stipend.

How we hire
Our process is deliberately short: a 30-minute intro call, a practical exercise or portfolio conversation relevant to the role, a team interview and a final conversation with a founder. We give a decision within a week of the final stage, and we give feedback either way.

Working at AIApply
We are remote-first with core collaboration hours across US time zones. We write things down, keep meetings rare and trust people to own outcomes. If you want to work on AI that changes something real for people rather than a demo, this is a good place to do it.

Responsibilities

Design and version prompt systems across product surfaces.
Build automated and human evaluation loops.
Benchmark models and recommend the right one per task.
Reduce hallucination and unsafe output with guardrails.
Tune for tone, accuracy and cost together.
Document prompt architecture for engineers.

Qualifications

2+ years working hands-on with LLMs in production. Strong writing and editorial judgement. Comfortable scripting in Python. Systematic approach to evaluation. Curiosity about model behaviour.

Required

Must be authorised to work in the United States without visa sponsorship. Remote within US time zones.

Skills

• Prompt engineering
• LLM evaluation
• Python
• Few-shot design
• Guardrails
• Model comparison
• Data annotation
• Content quality
• Experimentation

Benefits

• Fully remote-friendly within the US
• Competitive salary and meaningful equity
• Medical, dental and vision covered
• 401(k) with company match
• Unlimited PTO with a 3-week minimum
• $2,000 annual learning budget
• Home office and hardware stipend