Software Engineer - AI Tooling

This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for a Software Engineer - AI Tooling based in Canada.

As a Software Engineer on the AI Tooling team, you will help shape the next generation of AI-powered developer experiences and tools.
You will design, build, and maintain intelligent agents, Model Context Protocol (MCP) servers, agent skills, and AI-powered assistants.
Your work will make development platforms and products more accessible to AI agents, enabling developers to build smarter applications and workflows.
You will champion an evaluation-first engineering approach, ensuring that every tool is measured against clear quality, reliability, and performance benchmarks.
Working closely with Documentation, CLI, Frontend, SDK, and Infrastructure teams, you will contribute to a consistent and scalable developer experience.
You will also explore emerging AI technologies, experiment with new approaches, and turn promising innovations into production-ready solutions.
This is an opportunity to make a significant impact in a fast-moving, open-source-oriented environment alongside a globally distributed engineering team.

Accountabilities

Design, develop, and continuously improve AI-powered developer tools, including MCP servers, intelligent agents, agent skills, and dashboard assistants.

• Ensure new products and features are accessible to AI agents from launch by developing the necessary tools, skills, integrations, and evaluation frameworks.

• Explore emerging AI technologies and agent architectures, rapidly prototype new solutions, assess their effectiveness, and collaborate with the team to determine which innovations are suitable for production.

• Establish and promote an evaluation-first engineering culture by developing evaluation frameworks, instrumentation, and feedback loops to measure AI tool quality and effectiveness.

• Benchmark AI-powered tools against no-tool baselines, monitor performance, and define quality indicators and release criteria to prevent regressions.

• Analyse how developers and AI agents interact with existing tools and translate usage insights into improvements to interfaces, documentation, and overall functionality.

• Design and optimise how technical documentation and product knowledge are structured and exposed to AI agents, measuring their effectiveness and accessibility.

• Develop reusable patterns and tools that enable customers to integrate AI capabilities into their own applications, including MCP integrations with Edge Functions, vector embeddings, and AI agents running on Edge Functions.

• Enable cross-functional engineering teams to contribute to AI capabilities by providing clear contribution guidelines, templates, documentation, and review processes.

• Centralise shared AI logic and reusable components to encourage consistency and reduce duplicated development efforts across teams.

• Ensure production readiness through comprehensive testing, benchmarking, stress testing, and continuous reliability improvements.

• Collaborate with AI Tooling Infrastructure engineers on service hosting, authentication, scalability, and operational reliability.

• Work closely with Documentation, CLI, Frontend, SDK, and other engineering teams to deliver a seamless and consistent developer experience.

• Stay informed about developments in the AI ecosystem and identify opportunities to incorporate relevant technologies and practices into the platform.

Requirements:

• At least 5 years of professional software engineering experience.

• Strong proficiency in TypeScript and extensive knowledge of the JavaScript ecosystem, including npm, ES modules, bundlers, and compatibility considerations.

• Deep familiarity with the AI ecosystem, including current tools, agent architectures, development patterns, and their practical trade-offs.

• Ability to distinguish sustainable and effective AI engineering approaches from short-lived trends or unnecessary complexity.

• Previous experience building developer tools, product interfaces, or platform components used by other engineers.

• Experience designing, implementing, or working with evaluation frameworks to measure AI quality, reliability, and task success.

• Understanding of evaluation fundamentals, including baselines, performance variance, cost considerations, and measurable quality improvements.

• Strong technical judgment when identifying opportunities to use AI effectively while avoiding fragile, unnecessary, or overly complex solutions.

• Solid testing practices and experience validating software reliability under real-world conditions.

• Good knowledge of PostgreSQL and relational database principles.

• Excellent written communication skills and the ability to collaborate effectively across engineering, product, and documentation teams.

• Comfortable working in asynchronous, globally distributed teams and managing priorities independently.

• Ability to navigate ambiguity, adapt to rapidly evolving technologies, and deliver high-quality solutions in a fast-paced environment.

Additional experience that would be an advantage:

• Experience working with vector databases, embeddings, and semantic search technologies, particularly pgvector.

• Previous experience shipping customer-facing AI features, intelligent assistants, or autonomous agents.

• Experience designing technical documentation, structured knowledge bases, or information systems optimised for developers and AI agents.

• Familiarity with Braintrust or similar AI evaluation and tracing platforms, or experience implementing automated quality gates within CI/CD pipelines.

• Contributions to open-source projects or experience maintaining developer-focused tools and libraries.

• Experience collaborating across multiple product areas, engineering teams, or technical platforms.

Benefits:

• Fully remote working environment, with the flexibility to work from anywhere in the world.

• WeWork membership or co-working allowance to support access to a professional workspace.

• Employee Stock Option Plan (ESOP), giving every team member an opportunity to share in the organisation's long-term success.

• Technology allowance to equip your home office with the hardware and tools you need, including laptops, monitors, and headphones.

• Comprehensive health coverage, with 100% of employee health insurance costs covered and 80% of dependent coverage, wherever applicable.

• Annual company-wide off-sites in different international locations, offering opportunities for collaboration, networking, and team building.

• Flexible working hours within an asynchronous work culture that promotes autonomy and work-life balance.

• Annual professional development and education allowance to invest in courses, books, conferences, and other learning opportunities.

• Opportunity to work alongside a globally distributed team of approximately 400 professionals across more than 60 countries.

• Exposure to an open-source-first engineering culture that encourages innovation, knowledge sharing, and continuous learning.

• Opportunity to contribute to widely used developer infrastructure and shape the future of AI-powered software development.

How Jobgether works:

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Why Apply Through Jobgether?

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

#LI-CL1