MCP & Plug In Connectors Expert

1 month, 2 weeks ago
Contract
Senior
Artificial Intelligence and Machine Learning
Weekday

Weekday

Weekday helps companies hire engineers who are vouched by other software engineers, enabling passive income for engineers. They offer services like drafting outreach messages, shortlisting candidates, and conducting reference checks. Backed by Y Combin...

Construction & Engineering
11-50
Founded 2020

Description

  • Design realistic prompts that reflect complex, real-world personal workflows.
  • Execute multi-step tasks using AI while recording your screen for evaluation.
  • Use AI plugins and connectors throughout workflow execution.
  • Assess AI-generated outputs for practicality, personalization, reasoning quality, and usefulness.
  • Identify failures in context handling, tool use, constraint awareness, and recommendations.
  • Write detailed, structured evaluations of AI strengths, weaknesses, and improvement opportunities.
  • Develop and apply structured rubrics to measure AI performance consistently across task types.

Requirements

  • Must be based in the United States.
  • Strong hands-on experience with Model Context Protocol (MCP) and AI plugin/connector ecosystems.
  • Frequent use of AI plugins/connectors such as Google Drive, Expedia, and Notion.
  • At least 6 months of heavy personal use of large language models.
  • Experience using AI for multi-step planning, research, decision-making, and everyday personal workflows.
  • Strong analytical thinking, written communication, and attention to detail.
  • Ability to evaluate AI outputs for accuracy, usefulness, personalization, safety, and reasoning quality.
  • Willingness to sign a data-sharing consent agreement through DocuSign.
  • Experience designing, applying, or reviewing structured evaluation rubrics.
  • Preferred: 100+ hours of AI evaluation or quality assessment work.
  • Preferred: Deep familiarity with AI-assisted productivity workflows involving multiple connected applications.
  • Preferred: Experience identifying AI limitations and recommending improvements from real-world usage scenarios.
  • Desktop or laptop computer required; Chromebooks are not supported.
  • Able to complete assigned work within 24 hours of task assignment.
  • Expected commitment of 20+ hours per week.
  • H1-B and STEM OPT candidates are not supported.

Benefits

  • Compensation of $50-$190 per hour.
  • Fully remote work with flexible working hours.
  • Weekly payments based on approved work completed.
  • Trial period with potential for continued engagement based on performance.
  • Reasonable accommodations available throughout the application and engagement process.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Developer Engagement Team (Contract)

Roblox 1K-5K Internet Software & Services

Roblox is hiring a Developer Engagement contractor to support its global creator community by resolving escalations, coordinating communication, and helping developers succeed on the platform.

14 hours, 10 minutes ago

Freelance Agent Evaluation Engineer

Mindrift.ai: Be the “I” in AI Internet Software & Services

Mindrift is seeking experienced software developers for a project-based, remote opportunity creating and evaluating realistic coding tasks and tests for AI coding agents used by leading technology companies.

Cybersecurity Docker FastAPI JavaScript Kafka Machine Learning PostgreSQL Python React Redis TypeScript
15 hours, 25 minutes ago

Bilingual Customer Service Representative - Seasonal

CSC Generation 251-1K Internet Software & Services

Backcountry, part of CSC Generation, is hiring a bilingual Customer Service Representative in Mexico City or Estado de México to support customers by phone, document interactions, and resolve issues within service standards.

15 hours, 25 minutes ago

AI Trainer - Fluent Kazakh Speaker - Stuttgart, Germany

Prolific 51-250 Professional Services

Prolific is seeking fluent Kazakh speakers to evaluate AI-generated text for naturalness, authenticity, tone, and cultural fit, helping improve AI language models.

NLP
2 days, 14 hours 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