Full Stack Engineer

Job Title : Full Stack Engineer

Location : Remote - Toronto, Ontario, Canada

Job Type : Full Time

Our Client is seeking a talented Full‑Stack Engineer to help shape the future of autonomous, agent‑based AI systems. This role focuses on training and refining advanced Large Language Models (LLMs) to operate as proactive, multi‑step agents capable of designing, coordinating, and optimizing complex real‑world workflows. This opportunity is ideal for engineers who enjoy working across the stack and thrive at the intersection of backend systems, intelligent orchestration, and AI‑driven automation.

What You’ll Do

* Train and evaluate AI agents to handle complex, multi‑stage reasoning and orchestration tasks.

* Build and assess production‑grade systems with modular architectures, including data ingestion, logic processing, and reporting layers.

* Analyze multi‑turn system interactions and agent behavior, providing clear, high‑quality technical feedback.

* Identify edge cases, failure modes, and improvement opportunities to enhance system reliability, safety, and performance.

* Support integration of AI agents with live tools, databases, and external APIs.

What We’re Looking For

* 2+ years of experience in full‑stack development, backend engineering, AI automation, or complex systems integration.

* Strong proficiency in at least two programming languages such as Python, JavaScript, Go, or Java.

* Experience working with SQL databases and live, production (non‑mocked) environments.

* Hands‑on experience managing stateful, multi‑turn system interactions.

* Exceptional attention to detail and the ability to provide concise, high‑density technical feedback on complex behaviors.

Nice to Have

* Experience building multi‑stage coordination or orchestration workflows where data acquisition drives reasoned outputs.

* Hands‑on experience integrating AI agents with live tools and APIs (e.g., databases, email platforms, third‑party services).

* Comfort implementing persistent state and session tracking for long‑running agent tasks.

* Experience identifying subtle system risks such as privacy leaks, authority escalation, or indirect prompt injection issues