Full Stack Engineer, Agentic AI

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Full Stack Engineer, Agentic AI based in Canada.

Join a remote-first digital product engineering team building innovative, AI-powered applications for ambitious startups, established brands, and enterprise clients. In this role, you will combine full-stack engineering expertise with generative AI, large language models (LLMs), and agentic workflows to transform complex business challenges into production-ready solutions. You will work across the entire development lifecycle, from understanding client needs and designing technical architectures to deploying, testing, and optimizing scalable applications. Collaborating with experienced engineers, designers, and cross-functional teams, you will help deliver intelligent products that create measurable business value. The position offers exposure to diverse industries, modern technology stacks, and emerging AI capabilities. If you thrive in autonomous environments, enjoy solving challenging problems, and want to shape the next generation of AI-driven products, this opportunity offers meaningful technical ownership and continuous learning.

Accountabilities

• Client engagement and solution discovery: Collaborate directly with clients to understand their business objectives, technical environments, operational challenges, and product requirements, translating them into actionable engineering solutions.

• Full-stack application development: Architect, build, test, and deploy scalable applications using technologies such as TypeScript, React, Node.js, Python, and Go, integrating AI and data capabilities throughout the application stack.

• Agentic AI development: Design and implement AI-powered applications and agentic workflows, including integrations with model context protocol (MCP) servers, LLM tools, and intelligent automation systems.

• LLM integration and optimization: Host, configure, tune, and manage large language models and related services, selecting appropriate models, libraries, and infrastructure to meet performance, cost, and reliability requirements.

• AI-powered feature engineering: Develop intelligent capabilities such as chatbots, information extraction, document generation, semantic search, data normalization, and other AI-driven product features.

• AI quality assurance and experimentation: Establish testing infrastructure, structured experimentation workflows, and evaluation frameworks to validate model outputs, improve prompt performance, and ensure reliable agent behavior.

• MLOps and LLMOps: Apply engineering best practices for monitoring, testing, deployment, observability, and operational reliability across AI-enabled applications and services.

• Data engineering and infrastructure: Design and implement scalable data pipelines, data lakes, and supporting infrastructure to enable efficient data processing and AI-powered functionality.

• Technical decision-making: Evaluate architectural options, communicate technical trade-offs and risks transparently, and help clients make informed decisions about implementation strategies and technology investments.

• Cross-functional collaboration: Work closely with engineers, designers, and other stakeholders to deliver high-quality products while maintaining strong engineering standards and effective delivery practices.

• Continuous innovation: Stay informed about developments in generative AI, agentic systems, cloud technologies, and developer tooling, incorporating relevant innovations into client projects.

Requirements

• Professional experience: Approximately 4–6 years of experience as a Full Stack Engineer, with a proven track record of delivering and maintaining production software across the stack.

• Programming expertise: Strong experience with TypeScript and modern web technologies, including React and Node.js, alongside proficiency in Python or Go.