At a Glance
- Tasks: Develop and maintain innovative Python tools for evaluating AI agent behaviour.
- Company: Join Mindrift, where innovation meets opportunity in the AI space.
- Benefits: Earn up to $50/hour with flexible remote work options.
- Other info: Gain valuable experience and enhance your portfolio while working remotely.
- Why this job: Be part of an advanced AI project that shapes the future of technology.
- Qualifications: 4+ years of Python experience and a passion for problem-solving.
The predicted salary is between 36000 - 60000 £ per year.
At Mindrift, innovation meets opportunity. We believe in using the power of collective human intelligence to ethically shape the future of AI.
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 behaviour. 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
Requirements
- 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
Additional Qualifications
- 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)
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
MCP & Tools Python Developer - Agent Evaluation Infrastructure employer: Mindrift
Mindrift is an excellent employer for those seeking a flexible and rewarding role in the innovative field of AI mortgage underwriting. With competitive compensation and a focus on part-time project-based work, employees benefit from a supportive work culture that values expertise and encourages professional growth. Located in Edinburgh, Mindrift offers a unique opportunity to contribute to cutting-edge technology while maintaining a healthy work-life balance.
StudySmarter Expert Advice🤫
We think this is how you could land MCP & Tools Python Developer - Agent Evaluation Infrastructure
✨Tip Number 1
Network like a pro! Reach out to folks in the industry, attend meetups, and connect with people on LinkedIn. You never know who might have the inside scoop on job openings or can refer you directly.
✨Tip Number 2
Show off your skills! Create a GitHub repository showcasing your Python projects, especially those related to APIs or tools. This gives potential employers a taste of what you can do and sets you apart from the crowd.
✨Tip Number 3
Prepare for interviews by brushing up on your problem-solving skills. Practice coding challenges and be ready to discuss your thought process. Employers love to see how you tackle complex issues, especially in security and AI.
✨Tip Number 4
Don’t forget to apply through our website! It’s the best way to ensure your application gets seen. Plus, we’re always looking for passionate individuals who want to make an impact in the AI space.
We think you need these skills to ace MCP & Tools Python Developer - Agent Evaluation Infrastructure
Some tips for your application 🫡
Tailor Your Application:Make sure to customise your CV and cover letter for the role. Highlight your Python experience and any relevant projects that align with the job description. We want to see how your skills fit into our vision!
Showcase Your Problem-Solving Skills:In your application, share examples of how you've tackled complex challenges in the past. We love candidates who can think creatively and adapt to new situations, so let us know how you’ve done this before!
Be Clear and Concise:When writing your application, keep it straightforward. Use clear language and avoid jargon unless it's relevant. We appreciate good communication skills, so make sure your application reflects that!
Apply Through Our Website:We encourage you to submit your application directly through our website. It’s the best way for us to receive your details and ensures you’re considered for the role. Don’t miss out on this opportunity!
How to prepare for a job interview at Mindrift
✨Know Your Python Inside Out
Make sure you brush up on your Python skills, especially in backend development and tools. Be ready to discuss your past projects and how you've built APIs or testing frameworks. They’ll want to see your problem-solving skills in action!
✨Familiarise Yourself with MCP and Tools
Since the role involves working with Model Context Protocol (MCP), it’s crucial to understand its principles. If you have experience with similar structured agent-server interfaces, be prepared to share specific examples of how you’ve implemented them.
✨Show Off Your Communication Skills
You’ll be collaborating with QA and writers, so clear documentation and communication are key. Think of instances where you’ve successfully communicated complex ideas to non-technical team members and be ready to share those stories.
✨Prepare for Technical Challenges
Expect some technical questions or challenges during the interview. Brush up on Docker, Linux CLI, and HTTP-based communication. Practising coding problems related to these areas can help you feel more confident when tackling real-time scenarios.
