AI/ML Engineer — Agentic AI Systems

Accountabilities:

• • Build agentic AI workflows capable of interpreting PSA and RMM signals, coordinating vendor API calls, and supporting automated decision-making across customer environments.
  • Develop behavioral anomaly detection models using workflow activity, credential usage, tool-call sequences, and cross-platform interaction patterns.
  • Implement detection mechanisms for scope escalation, abnormal decision paths, unexpected tool usage, and unusual output volumes.
  • Build evaluation harnesses and benchmarking pipelines to assess model and agent behavior, quality, latency, reliability, and safety.
  • Translate relevant machine learning and systems research into tested, maintainable production implementations.
  • Contribute to OpenAPI-based connector generation and integration workflows across IT management, security, and MSP platforms.
  • Integrate AI workloads with durable execution systems to support retries, partial failures, recovery, and long-running workflows.
  • Partner with platform, security, and product teams to implement monitoring, fallbacks, permissions, guardrails, and auditability for AI-powered capabilities.
  • Help improve the reliability, scalability, observability, and operational readiness of AI systems running in production environments.

  Requirements

  • Experience developing and operating production AI or machine learning systems using Python or a comparable programming language.
  • Hands-on experience building LLM or agent workflows with LangChain, LlamaIndex, or a similar orchestration framework.
  • Experience integrating model providers such as Amazon Bedrock, OpenAI, Vertex AI, or comparable platforms into production applications.
  • Experience developing evaluation harnesses, benchmark pipelines, automated tests, or other mechanisms for assessing model and agent behavior.
  • Demonstrated ability to apply machine learning or systems research techniques to production software.
  • Experience with behavioral anomaly detection, time-series analysis, statistical baselining, or outlier detection is an advantage.
  • Familiarity with event-driven architectures and technologies such as Kafka is preferred.
  • Experience with Temporal or another durable workflow orchestration platform is a plus.
  • Knowledge of ClickHouse or another columnar data store used for analytical workloads is beneficial.
  • Experience with API integrations, OpenAPI tooling, connector-generation pipelines, workflow automation, or enterprise security technologies is advantageous.
  • Familiarity with MSP tooling, IT operations platforms, or security products is a strong plus.
  • Strong problem-solving and analytical abilities, with the ability to translate complex technical concepts into reliable production solutions.
  • Ability to collaborate effectively across engineering, platform, security, and product teams in a fast-paced environment.

  Benefits

  • Competitive base salary of CAD $160,000–$240,000 per year.
  • Additional rewards and benefits may be available depending on the role and individual impact.
  • Opportunity to work on advanced agentic AI, machine learning, and enterprise automation technologies.
  • Hands-on exposure to LLM orchestration, behavioral intelligence, evaluation systems, and production AI infrastructure.
  • Opportunity to collaborate with multidisciplinary platform, security, and product teams.
  • High-impact role within a fast-growing technology environment.
  • Full-time position based in Toronto, Canada.
  • Equal employment opportunity and a commitment to a diverse and inclusive workplace.