MCP & Tools Python Developer - Agent Evaluation Infrastructure

hace 6 días

Ciudad de México, Ciudad de México Mindrift A tiempo completo

This opportunity is only for candidates currently residing in the specified country. Your location may affect eligibility and rates. Please submit your resume in English and indicate your level of English proficiency.

At Mindrift, innovation meets opportunity. We believe in using the power of collective human intelligence to ethically shape the future of AI. 

What we do

The Mindrift platform, launched and powered by Toloka, connects domain experts with cutting-edge AI projects from innovative tech clients. Our mission is to unlock the potential of GenAI by tapping into real-world expertise from across the globe.

Who we're looking for

Calling all security researchers, engineers, and penetration testers with a strong foundation in problem-solving, offensive security, and AI-related risk assessment.

If you thrive on digging into complex systems, uncovering hidden vulnerabilities, and thinking creatively under constraints, join us 

We're looking for someone who can bring a hands-on approach to technical challenges, whether breaking into systems to expose weaknesses or building secure tools and processes. We value contributors with a passion for continuous learning, experimentation, and adaptability. 

About the project

We're on the hunt for hands-on Python engineers for a new project focused on developing Model Context Protocol (MCP) servers and internal tools for running and evaluating agent behavior. You'll implement base methods for agent action verification, integrate with internal and client infrastructures, and help fill tooling gaps across the team.

What you'll be doing:

  • Developing and maintaining MCP-compatible evaluation servers
  • Implementing logic to check agent actions against scenario definitions
  • Creating or extending tools that writers and QAs use to test agents
  • Working closely with infrastructure engineers to ensure compatibility
  • Occasionally helping with test writing or debug sessions when needed

Although we're only looking for experts for this current project, contributors with consistent high-quality submissions may receive an invitation for ongoing collaboration across future projects. 

How to get started:

Apply to this post, qualify, and get the chance to contribute to a project aligned with your skills, on your own schedule. Shape the future of AI while building tools that benefit everyone.

Requirements

The ideal contributor will have:

  • 4+ years of Python development experience, ideally in backend or tools
  • Solid experience building APIs, testing frameworks, or protocol-based interfaces
  • Understanding of Docker, Linux CLI, and HTTP-based communication
  • Ability to integrate new tools into existing infrastructures
  • Familiarity with how LLM agents are prompted, executed, and evaluated
  • Clear documentation and communication skills - you'll work with QA and writers

We also value applicants who have:

  • Experience with Model Context Protocol (MCP) or similar structured agent-server interfaces
  • Knowledge of FastAPI or similar async web frameworks
  • Experience working with LLM logs, scoring functions, or sandbox environments
  • Ability to support dev environments (devcontainers, CI configs, linters)
  • JS experience
Benefits
  • Get paid for your expertise, with rates that can go up to $21/hour depending on your skills, experience, and project needs.
  • Take part in a flexible, remote, freelance project that fits around your primary professional or academic commitments.
  • Participate in an advanced AI project and gain valuable experience to enhance your portfolio.
  • Influence how future AI models understand and communicate in your field of expertise.

  • Freelance Agent Evaluation Analyst

    hace 6 días

    Ciudad de México, Ciudad de México Mindrift A tiempo completo

    This opportunity is only for candidates currently residing in the specified country. Your location may affect eligibility and rates. Please submit your resume in English and indicate your level of English proficiency.At Mindrift, innovation meets opportunity. We believe in using the power of collective human intelligence to ethically shape the future of...

  • Golang Developer

    hace 4 días

    Ciudad de México, Ciudad de México GFT A tiempo completo

    What are we are looking for?Golang DeveloperResponsabilities:Complete peer code reviews and provide written and verbal feedback in EnglishReview AI generated feedback generated during the code review processUse GenAI tools to generate recommendations to improve user codeProvide feedback and participate in discussions to determine how to improve the...

  • Python Senior Backend Developer

    hace 5 días

    Ciudad de México, Ciudad de México Definity First A tiempo completo

    We are looking for a highly skilled Python Senior Backend Developer to join our team and contribute to high-impact initiatives with one of our US-based clients. We're seeking someone motivated, detail-oriented, and ready to own complex backend challenges. The ideal candidate is a proactive problem-solver who thrives in dynamic, collaborative environments and...

  • Product Analyst

    hace 6 días

    Ciudad de México, Ciudad de México Agent A tiempo completo

    Job Title: Product Analyst (Academic Background)Compensation: $3,500- 4,500/month, (salary depending on experience)Location: Remote, LATAMWorking hours: 9-5pm PSTAbout the Company:Our client is a neuroscience-based technology company dedicated to revolutionizing health behavior change through a positive, iterative approach to habit formation. Their...

  • C C+ Developer

    hace 4 días

    Ciudad de México, Ciudad de México GFT A tiempo completo

    What are we are looking for?C DeveloperResponsabilities:Complete peer code reviews and provide written and verbal feedback in EnglishReview AI generated feedback generated during the code review processUse GenAI tools to generate recommendations to improve user codeProvide feedback and participate in discussions to determine how to improve the customer's...

  • DevOps Engineer

    hace 4 días

    Ciudad de México, Ciudad de México Tachyon Technologies A tiempo completo

    Job Title-: DevOps EngineerLocation-: Mexico City  (2-3 days Onsite)Provisioning and managing AWS infrastructure using Infrastructure as Code (IaC) tools such as Terraform and CloudFormationMonitoring and logging using AWS CloudWatchImplementing AWS security best practices, defining policies, and ensuring complianceIdentifying and driving opportunities for...

  • Growth Operations Manager

    hace 2 semanas

    Ciudad de México, Ciudad de México Agent A tiempo completo

    Position: Growth Operations ManagerLocation: Remote (LATAM) – Must overlap Eastern Time (EST) working hoursCompany OverviewWe are a growth marketing consultancy that partners with fast-scaling brands. Acting as a fractional marketing team and strategic advisor, we help clients solve their most critical marketing challenges—moving from guesswork to...

  • Onprem Infrastructure Engineer

    hace 5 días

    Ciudad de México, Ciudad de México Fixity Technologies A tiempo completo

    Te comparto el siguiente requerimiento. Es para trabajar en CDMX es totalmente en oficinas de Mastercard. Salario max de $90k gross Onprem Infrastructure Engineer - Work at arcus offices - This position must be able to communicate fluently in English and Spanish, must have a strong sense of urgency and an eye for detai Onprem Infrastructure Engineer. 1...

  • AI Developer

    hace 5 días

    Ciudad de México, Ciudad de México NEORIS A tiempo completo

    NEORIS es un acelerador Digital que ayuda a las compañías a entrar en el futuro, teniendo 20 años de experiencia como Socios Digitales de algunas de las mayores compañías del mundo. Somos más de 4,000 profesionales en 11 países, con nuestra cultura multicultural de startup en donde cultivamos innovación, aprendizaje continuo para crear soluciones de...

  • Jira Developer

    hace 6 días

    Ciudad de México, Ciudad de México Blue Ridge Consultants A tiempo completo

    We're seeking a Jira Developer focused on building complex Jira Automations and ScriptRunner solutions. You'll design and implement advanced workflows, provide technical guidance and recommendations to our team, and collaborate within a supportive, team-oriented culture.Must-Have ExperienceStrong English-language communication skillsJira Software (JSW)...