Profile cover
A

AI Sarcasm and Irony Detection Engineer

Adam Li

Full-time · Job · Lisbon

About the role

As a fully async team spread across eight time zones, we believe great engineers can do great work without ever sharing a timezone with their manager. Our clients use our NLP APIs to analyze customer feedback and social mentions at scale. You will build models that detect sarcasm and irony in short-form text, a persistent blind spot in our current sentiment pipeline that causes clients to misread negative feedback as positive. We don't care where you work from. We care about output, clear communication, and ownership. The impact lands directly in client dashboards: fewer misclassified mentions, more trustworthy sentiment scores, and fewer support escalations from confused client teams.

Responsibilities

  • Build sarcasm and irony detection models for short-form text
  • Integrate detection output into the sentiment pipeline
  • Reduce misclassification rate on negative sarcastic feedback
  • Document model limitations for client-facing teams
  • Communicate progress async across time zones

Requirements

  • 3+ years working with NLP or sentiment analysis systems
  • Experience with hugging face and PyTorch
  • Comfortable working fully async
  • Strong statistical evaluation skills

Benefits

  • Fully remote and async
  • Flexible hours across any time zone
  • Health insurance stipend
  • Annual team offsite

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Job Type

Full-time

Level

Mid-Level

Language

English

Salary Range

$100k – $130k / year

AI Expertise

NLP & Prompt Engineering

Skills

python hugging face pytorch statistics

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile

Interested in this role? Create your free profile to apply.

Apply — create free profile