Project Lion - Lead Prompt Engineer - United States (Remote, Part-Time)

1 hour, 55 minutes ago
Freelance
Lead
Data Science and Analytics
Welocalize

Welocalize

Welocalize provides translation and localization services to help businesses reach global audiences with precision and efficiency.

Professional Services
1K-5K
Founded 1997
$34M raised

Description

  • Lead and manage the technical migration process from templates to LLM autoraters.
  • Use Automatic Prompt Generation (APG) tools to create baseline prompts for complex parent-child template clusters.
  • Run and supervise Automated Prompt Optimization (APO) workflows and identify deadlocks or plateaus in outputs.
  • Manually draft, test, and refine prompts for complex architectures, anti-patterns, and edge cases when tooling is unavailable or broken.
  • Design and refine manual prompt solutions for difficult edge-case scenarios.
  • Monitor shadowbot runs to ensure human and LLM rating disagreements are generated and tracked appropriately.
  • Run prompt versions against gold data to evaluate autorater quality against the human crowd baseline.
  • Calculate and report model quality metrics such as F1 score, precision, and recall.
  • Draft technical launch readiness documentation and final launch certification justifications.
  • Mentor junior engineers and help shape the strategy for ongoing AI system improvement.

Requirements

  • Native fluency in English.
  • Must be based in the United States.
  • Master’s or Doctorate degree in Computer Science, Data Science, Computational Linguistics, Human-Computer Interaction (HCI), Cognitive Science, or a related analytical field.
  • At least 7 years of experience as a Prompt Engineer.
  • Proven experience tuning LLMs for strict, structured outputs and complex classification tasks.
  • Familiarity with chain-of-thought and few-shot learning approaches.
  • Strong proficiency in identifying error patterns, analyzing model performance, and using SQL or other data analytics tools.
  • Ability to quickly learn and master proprietary tools with minimal supervision.
  • Excellent verbal and written communication skills.
  • Familiarity with enterprise-grade LLM interfaces such as the Goose API (preferred).
  • Experience in AI model evaluation, data science, computational linguistics, or software engineering (preferred).
  • Hands-on experience with Automated Prompt Optimization (APO) systems or tuning workflows (preferred).
  • Linguistic expertise, including understanding of semantics and logic (preferred).

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Legal Knowledge Engineer

Agiloft 51-250 Capital Markets

Agiloft is hiring a remote Legal Knowledge Engineer in Canada to help shape AI-powered contract lifecycle management products by translating commercial legal expertise into real-world AI workflows and product improvements.

Generative AI LLM MLOps
1 hour, 55 minutes ago

Legal Knowledge Engineer

Agiloft 51-250 Capital Markets

Agiloft is hiring a remote Legal Knowledge Engineer to help shape its AI-powered contract lifecycle management platform by applying legal expertise to real-world contract workflows and product development.

Generative AI MLOps
10 hours, 40 minutes ago

Content Designer, Personalization

Spotify Media

Spotify is hiring a Content Designer for its Personalization Design team to shape the language and content systems behind AI-driven music discovery experiences at global scale.

Generative AI LLM
6 days, 2 hours ago

AI Prompt Engineering Lead (Agentic AI & Hiring Automation) - Remote

Cynet Group 251-1K Professional Services

Senior AI Prompt Engineering Lead at Cynet Corp to architect, govern, and optimize Agentic AI systems that autonomously recruit, evaluate, and interact with talent using production-grade LLM architectures.

1 month, 3 weeks ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers