Senior AI Engineer

MarkiTech; Toronto; Hybrid; CAD 120,000 - 190,000; Full time

Job summary

MarkiTech is seeking a hands-on Senior AI Engineer to architect and build enterprise-grade AI agents for regulatory compliance. You will shape agentic AI workflows, evaluate agents, and collaborate with business SMEs to translate requirements into scalable AI solutions.

The role emphasizes production-ready Python code, AI architecture, and integration with AWS Bedrock, with a hybrid work model and enterprise-scale impact.

Qualifications

• Hands-on experience building Generative AI / LLM applications.
• Advanced Python development skills and production experience.
• Practical experience with AWS Bedrock and AWS-based AI architectures.
• Experience designing AI agents, agentic workflows or multi-agent systems.
• Experience building LLM evaluation frameworks (quality, hallucination, accuracy).
• Strong understanding of prompt engineering, model selection, orchestration and deployment.

Responsibilities

• Design and develop AI agents and multi-agent workflows for regulatory use cases.
• Build AI solutions using Python and AWS Bedrock.
• Design architecture for agent orchestration, reasoning, and workflow execution.
• Develop evaluation frameworks to measure agent outputs for quality and reliability.
• Identify and monitor compliance drift over time in production systems.
• Collaborate with SMEs to translate requirements into AI workflows.
• Develop production-quality components for integration into broader platforms.
• Support testing, iteration and continuous improvement of AI agent performance.

Skills

Generative AI / LLM apps

Python development

AWS Bedrock

AI agents / multi-agent systems

AI evaluation frameworks

Prompt engineering

Tools

AWS Bedrock tooling

Orchestration frameworks

Job description

Senior AI Engineer - Agentic AI & AWS Bedrock

Engagement: Contract
Work Model: Hybrid / Flexible Location
Project: Enterprise Regulatory Compliance AI Platform

Overview

We are seeking an experienced senior AI engineer** to support the development of an enterprise-grade regulatory compliance platform using agentic AI.

The solution will use intelligent agents to help organizations manage business compliance, maintain ongoing adherence to regulatory requirements, and identify potential compliance drift over time.

The successful candidate will work closely with business and regulatory subject matter experts while taking a hands-on role in the AI architecture, modeling, evaluation and implementation of the platform.

Key Responsibilities

• Design and develop AI agents and multi-agent workflows for regulatory compliance use cases.
• Build AI solutions using Python and AWS Bedrock.
• Design the underlying architecture for agent orchestration, reasoning, and workflow execution.
• Develop robust AI evaluation frameworks to measure accuracy, reliability, consistency, and quality of agent outputs.
• Implement mechanisms to identify and monitor compliance drift over time.
• Collaborate with regulatory and business SMEs who will validate agent outputs and business rules.
• Develop production-quality components that can integrate into the broader DLO platform.
• Support testing, iteration and continuous improvement of AI agent performance.

Required Experience

• Strong hands-on experience developing Generative AI / LLM applications.
• Advanced Python development skills.
• Practical experience with AWS Bedrock and AWS-based AI architectures.
• Experience designing and implementing AI agents, agentic workflows or multi-agent systems.
• Experience building LLM evaluation frameworks, including approaches for measuring output quality, hallucination, accuracy and reliability.
• Strong understanding of prompt engineering, model selection, orchestration and production AI deployment.
• Experience taking AI solutions from prototype through production implementation.
• Ability to work directly with business and domain SMEs to translate requirements into AI workflows.

Preferred Experience

• Experience with enterprise compliance, governance, risk, or regulatory applications.
• Experience with AI guardrails, responsible AI, and model governance.
• Familiarity with RAG, knowledge bases, embeddings, and enterprise data integration.
• Experience monitoring AI systems for performance degradation or drift.
• Previous consulting, enterprise or professional-services experience.

Ideal Profile

We are looking for a hands‑on senior AI engineer rather than a purely advisory architect. The ideal candidate can design the solution architecture while also building, testing and evaluating production‑grade AI agents.

The role will operate as part of an integrated client/partner team, with regulatory subject matter expertise provided by the client and the AI engineering team responsible for translating that expertise into reliable, scalable AI capabilities.