Agentic AI Engineer - Regina

Job Description

Requirements
- -----------

### Must have:

### - We bring at least 2 years of experience in backend engineering, AI automation, or integrating complex systems. - We have proven experience building and maintaining production-ready software with clear modular separation, such as distinct services for parsing, logic, and reporting. - We are proficient in at least two major programming languages, such as Python, JavaScript, Go, or Java, and we have worked with SQL databases. - We have practical experience building for live, non-mocked environments and managing multi-turn system interactions. - We demonstrate exceptional attention to detail and can deliver concise, high-signal technical feedback on sophisticated system behavior. - We ideally have experience designing multi-stage coordination workflows where data gathering leads to reasoned outcomes. - We are comfortable integrating agents with live tools and APIs such as Supabase and Gmail to solve practical problems. - We have experience implementing persistent state and session tracking using MEMORY.md to monitor agent progress. - We can identify subtle issues such as privacy exposure, authority escalation, and indirect prompt injection.

Responsibilities:
- ----------------

- We help train advanced AI systems by providing human feedback that improves autonomous agent performance. - We contribute to projects focused on teaching models how to plan, coordinate, and optimize complex real-world architectural workflows. - We build and refine multi-step agent behaviors for proactive, goal-driven tasks. - We work on orchestration challenges that require structured reasoning and effective system coordination. - We evaluate system behavior in live environments and provide detailed feedback on performance and edge cases. - We support the development of generative systems by helping them operate more reliably across realistic scenarios. - We analyze complex interactions and surface failures that affect safety, privacy, or control. - We collaborate on tasks that require integrating data acquisition, processing, and output generation into coherent workflows.
- ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Company:
- -------

We support innovative companies by using human feedback to improve AI agents and help train some of the most advanced generative systems in the world. Our work centers on collaborative projects with leading AI organizations, where we focus on building agents that can handle proactive, multi-step, real-world workflows with greater accuracy and reliability. We value strong technical depth, careful observation, and clear feedback, and we welcome people who are passionate about orchestration or experienced in software development to help shape the future of autonomous agents.
- -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------