AI Engineer (Superhuman Mail)

CanadaRemoteFull-timemid

Machine Learning EngineerData

1 views0 saves0 applied

Apply Now

Quick Summary

Key Responsibilities

Build and continuously improve the Model Context Protocol (MCP) infrastructure, developing new tools, standards, and capabilities that enable AI agents to take meaningful actions on behalf of users.

Requirements Summary

4–6+ years of software engineering experience, with a solid foundation in backend development. Proficiency in Python or TypeScript; experience with Go is an advantage.

Technical Tools

Machine Learning EngineerData

Join a forward-thinking engineering team developing intelligent AI-powered productivity experiences that transform how people communicate and work. As an AI Engineer, you will help build the backend infrastructure and applied AI capabilities powering next-generation email experiences. You will design agentic workflows, develop intelligent tools, and enhance personalization to make AI assistants more useful and context-aware. Working across multiple AI models and technologies, you will contribute to selecting the best solutions for different tasks. You will also build evaluation systems that ensure quality, reliability, and continuous improvement. This remote-flexible opportunity offers significant technical ownership, close collaboration, and the freedom to shape innovative AI products.

As an AI Engineer, you will help develop and scale the intelligent infrastructure behind advanced email and AI-powered productivity experiences. Your main responsibilities will include:

Build and continuously improve the Model Context Protocol (MCP) infrastructure, developing new tools, standards, and capabilities that enable AI agents to take meaningful actions on behalf of users.
Design, implement, and scale agentic workflows and personalized AI features.
Develop evaluation frameworks to measure AI performance, assess output quality, and identify regressions as prompts, models, and tools evolve.
Evaluate and select the most appropriate AI models for different use cases, exploring solutions from leading providers and open-source communities.
Collaborate with cross-functional engineering and product teams to provide reusable AI tools and infrastructure that accelerate feature development.
Deliver solutions quickly, learn from implementation results, and adapt to evolving technologies and industry developments.
Contribute to machine learning strategy where relevant, including data collection approaches and data generation methods.

Requirements

~1 min read

The ideal candidate combines strong backend engineering expertise with practical experience developing and deploying AI-powered applications. You should demonstrate technical curiosity, adaptability, and a strong sense of ownership. Key qualifications include:

4–6+ years of software engineering experience, with a solid foundation in backend development.
Proficiency in Python or TypeScript; experience with Go is an advantage.
Hands-on experience building and deploying production-ready applications powered by Large Language Models (LLMs), including AI agents and agentic workflows.
Experience developing evaluation frameworks to measure, monitor, and improve LLM performance and quality.
Familiarity with Model Context Protocol (MCP) servers and tools, or a strong willingness to develop expertise in this area.
Working knowledge of machine learning concepts and the ability to assess model capabilities, trade-offs, and suitability for different tasks.
A practical, builder-oriented mindset, with an interest in applying AI rather than focusing exclusively on research.
Comfort working in ambiguous environments and adapting quickly to changing priorities.
Enthusiasm for AI and experience using AI tools to improve personal productivity and team effectiveness.
Strong ownership, initiative, problem-solving abilities, and a continuous learning mindset.