Talent.com
MCP & Tools Python Developer - Agent Evaluation Infrastructure
MCP & Tools Python Developer - Agent Evaluation InfrastructureMindrift • Cologne, NRW, DE
MCP & Tools Python Developer - Agent Evaluation Infrastructure

MCP & Tools Python Developer - Agent Evaluation Infrastructure

Mindrift • Cologne, NRW, DE
Vor 4 Tagen
Anstellungsart
  • Homeoffice
  • Quick Apply
Stellenbeschreibung

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 $50 / 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.
  • Jobalert für diese Suche erstellen

    Python Developer • Cologne, NRW, DE

    Ähnliche Stellen
    Low-Code Consultant (m / w / d) Microsoft Power Platform

    Low-Code Consultant (m / w / d) Microsoft Power Platform

    HanseVision GmbH - Bechtle Group • Cologne, DE
    Unser Ziel : Effiziente, sichere und skalierbare Anwendungen, die Unternehmen befähigen, flexibel und zukunftsfähig zu arbeiten. Dabei setzen wir auf Low-Code-Ansätze, um schnelle, agile und kostenef...Mehr anzeigen
    Zuletzt aktualisiert: vor 10 Tagen • Gesponsert
    Lead Software Engineer

    Lead Software Engineer

    JUPUS GmbH • Cologne, North Rhine-Westphalia, Germany
    Homeoffice
    Quick Apply
    Lead Software Engineer (Full-Stack, Python-first).Europe’s fastest-growing legal tech companies scale its software platform end to end. Our AI-powered products are already in market; now we need rob...Mehr anzeigen
    Zuletzt aktualisiert: vor über 30 Tagen
    Senior Cloud Infrastructure Engineer (m / w / d)

    Senior Cloud Infrastructure Engineer (m / w / d)

    Polarstern Experts • Cologne, North Rhine-Westphalia, Germany
    Quick Apply
    Für Workloads, die weiterhin virtuelle Maschinen statt Kubernetes erfordern, schaffen wir eine moderne Infrastruktur in der AWS-Cloud. Du hast Lust dich darauf zu spezialisieren? Dann bewirb dich un...Mehr anzeigen
    Zuletzt aktualisiert: vor 5 Tagen
    IT Solution Engineer Cloud / Network (m / w / d)

    IT Solution Engineer Cloud / Network (m / w / d)

    netgo group GmbH • Köln, DE
    Werde auch du "part of netgo group" - einem der größten IT-Dienstleister Deutschlands.Mitarbeiter •innen an zahlreichen Standorten in ganz Deutschland erwarten dich als neues Teammitglied.Kunden – d...Mehr anzeigen
    Zuletzt aktualisiert: vor 6 Tagen • Gesponsert
    DevOps Engineer Healthcare Platform (mfd)

    DevOps Engineer Healthcare Platform (mfd)

    LOWTeq GmbH • Cologne, North Rhine-Westphalia, Germany
    Are you interested in the healthcare industry and experienced in improving the automation of development processes Do you want to contribute to impactful new projects Then we have an exciting oppor...Mehr anzeigen
    Zuletzt aktualisiert: vor über 30 Tagen • Gesponsert
    Senior Application Engineer, Microsoft 365 / Power Platform (m / w / d)

    Senior Application Engineer, Microsoft 365 / Power Platform (m / w / d)

    Flossbach von Storch SE • bonn, nordrhein-westfalen, de
    Senior Application Engineer Microsoft 365 & Power Platform (m / w / d).Bei Flossbach von Storch kümmern wir uns mit ca.Mitarbeitenden um das Vermögen von etwa einer Million Menschen – unabhängig davon,...Mehr anzeigen
    Zuletzt aktualisiert: vor 8 Tagen • Gesponsert
    IT-Engineer Operations - Cloud & Infrastructure (m / w / d)

    IT-Engineer Operations - Cloud & Infrastructure (m / w / d)

    E.ON Grid Solutions GmbH • Essen, DE
    Eine Aufgabe, die herausfordert.Als integraler Bestandteil unseres Teams im Bereich Metering Solutions wirst du eine Schlüsselrolle in der Transformation und dem Betrieb unserer IT-Infrastruktur sp...Mehr anzeigen
    Zuletzt aktualisiert: vor 1 Tag • Gesponsert
    C# / WPF Developer (m / f / d)

    C# / WPF Developer (m / f / d)

    Optimus Search • Cologne, DE
    Über uns About usWith over 25 years of industry experience and strong partnerships with leading global tech companies, our client specializes in developing cutting-edge enterprise applications for ...Mehr anzeigen
    Zuletzt aktualisiert: vor 8 Tagen • Gesponsert
    OpenStack Cloud Engineer (m / w / d)

    OpenStack Cloud Engineer (m / w / d)

    Burda DigitalSystems GmbH • Cologne, DE
    Außerdem verfügt BurdaSolutions über eine hohe Kompetenz in den Bereichen Business Intelligence, CRM, ERP und mobile Applikationen. Offenburg oder München, Vollzeit, unbefristet Was dich bei ...Mehr anzeigen
    Zuletzt aktualisiert: vor über 30 Tagen • Gesponsert
    Solution Engineer – Subscription & Billing Platform (m / w / d)

    Solution Engineer – Subscription & Billing Platform (m / w / d)

    ista SE • Essen, DE
    Solution Engineer – Subscription & Billing Platform (m / w / d).IT / Berlin, Dircksenstraße / Hybrid / Vollzeit / iSE02549. Wir bei ista unter­stützen Eigen­tümer : innen und Ver­walter : innen von Immo­bi­...Mehr anzeigen
    Zuletzt aktualisiert: vor über 30 Tagen • Gesponsert
    Senior Backend Engineer Python (mwd)

    Senior Backend Engineer Python (mwd)

    Ströer SE & Co. KGaA (Ströer Gruppe) • Köln, North Rhine-Westphalia, Germany
    Du entwickelst und verbesserst das neue führende Stammdatensystem im Bereich Außenwerbung.Du analysierst Anforderungen des Fachbereichs findest passende Lösungsmöglichkeiten und...Mehr anzeigen
    Zuletzt aktualisiert: vor 14 Tagen • Gesponsert
    DevOps Engineer (m / f / d)

    DevOps Engineer (m / f / d)

    Alphawave GmbH • Oberhaussen, Germany
    Experience : 5+ years in Software Engineering, with at least 3 years focused on DevOps, Release Engineering, or Infrastructure. Architectural Mindset : Proven track record of designing and implementin...Mehr anzeigen
    Zuletzt aktualisiert: vor 1 Tag • Gesponsert
    Coding the future of Life Sciences (Senior) Infrastructure Platform Engineer – DevEx (m|f|d)

    Coding the future of Life Sciences (Senior) Infrastructure Platform Engineer – DevEx (m|f|d)

    Miltenyi Biotec • Bergisch Gladbach, North Rhine-Westphalia, Germany
    Software shapes the world in so many ways and is becoming more and more important to define the future of health care.Become part of our Software Development Team and help us change peoples lives f...Mehr anzeigen
    Zuletzt aktualisiert: vor über 30 Tagen • Gesponsert
    Product / Project Lead - Discovery Platform with Bio- / Cheminformatics Expertise (gn) - Bonn, Munich

    Product / Project Lead - Discovery Platform with Bio- / Cheminformatics Expertise (gn) - Bonn, Munich

    Mycolever • Rheinbach, North Rhine-Westphalia, Germany
    Quick Apply
    At Mycolever, we are building the powerhouse for sustainable fungal biocompounds.We unlock the Fungal Kingdom with our biocompound discovery platform and aim to provide performant ingredients that ...Mehr anzeigen
    Zuletzt aktualisiert: vor über 30 Tagen
    Data Engineer for Quantitative Risk Analysis & Valuation Management - Python & Azure (f / m / d)

    Data Engineer for Quantitative Risk Analysis & Valuation Management - Python & Azure (f / m / d)

    E.ON Energy Markets GmbH • Essen, Essen (Kreis), Nordrhein-Westfalen
    Responsibilities • Work in a highly experienced, collaborative, international, fun team that sits at the heart of E.ON’s new energy trading and procurement unit. Help shape the quantitative risk man...Mehr anzeigen
    Zuletzt aktualisiert: vor 14 Tagen • Gesponsert
    AI Prompt Evaluators with Portuguese | On-site in Essen

    AI Prompt Evaluators with Portuguese | On-site in Essen

    TELUS Digital Europe • Essen, de
    AI Prompt Evaluators with Portuguese | On-site in Essen.TELUS Digital AI is looking for AI Prompt Evaluators with fluency in Portuguese to support the development of AI technologies on-site in our ...Mehr anzeigen
    Zuletzt aktualisiert: vor über 30 Tagen • Gesponsert
    Project Engineer EMEA (f / m / d)

    Project Engineer EMEA (f / m / d)

    Riedel Communications • Wuppertal, Nordrhein-Westfalen, Deutschland
    Quick Apply
    Wuppertal, Deutschland - Hybrid.RIEDEL Communications is the leading provider of live production tools in the media, sports and entertainment sectors. To cover our customers' needs holistically, w...Mehr anzeigen
    Zuletzt aktualisiert: vor über 30 Tagen
    Senior Application Engineer, Microsoft 365 / Power Platform (gn)

    Senior Application Engineer, Microsoft 365 / Power Platform (gn)

    Flossbach von Storch SE • Köln, Nordrhein-Westfalen, Deutschland
    Senior Application Engineer Microsoft 365 & Power Platform (m / w / d).Bei Flossbach von Storch kümmern wir uns mit ca.Mitarbeitenden um das Vermögen von etwa einer Million Menschen – unabhängig davon,...Mehr anzeigen
    Zuletzt aktualisiert: vor 9 Tagen • Gesponsert