Synopsis of the RoleIn this role, you will be the hands-on builder translating complex automation blueprints into production-grade, stateful agentic workflows. Working within our secure, globally integrated, and highly regulated architecture, you will push the boundaries of what autonomous systems can do-balancing cutting-edge LLM orchestration with absolute data security and deterministic guardrails.
What you will doCore Agent Engineering & Creative Prototyping
- Build Complex Agentic Loops: Develop, test, and deploy robust multi-agent architectures and stateful graph workflows using LangGraph, Google ADK frameworks with our internal agentic or UiPath platforms.
- State & Memory Management: Implement advanced short-term and long-term memory systems, utilizing vector databases and custom checkpointing to ensure agents maintain flawless context across long-running, asynchronous tasks.
- Creative Problem Solving: Apply a customer-centric, design-thinking lens to architecture challenges. You will actively design solutions and rapidly prototype creative, fact-based AI systems that solve ambiguous, non-linear business problems.
- Optimize Model Execution: Optimize agentic loops for latency, context-window management, and token consumption, making strategic decisions on when to deploy multi-LLM orchestration, lightweight local models, or high-performance frontier LLMs.
Tooling, APIs & Cloud Deployment
- Equip Agents with Tools: Build clean, secure integrations allowing LLMs to interact with internal APIs, databases, modern microservices, and third-party SaaS platforms via advanced function-calling.
- Cross-Functional Collaboration: Partner directly with infrastructure, product, business and DevOps teams to containerize, deploy, and scale your AI agents securely within a cloud environment, ensuring smooth production delivery.
- Bridge AI & RPA: Partner with our automation squads to integrate agentic decision-making with enterprise-grade UiPath workflows, effectively turning traditional RPA bots into intelligent, cognitive executioners.
Regulated Security & Code Quality
- Code for a Regulated Space: Design agent workflows that strictly adhere to enterprise security, compliance, and data governance standards, ensuring auditable decision logs and safe handling of sensitive data.
- Code Quality & Governance: Build and follow strict software development best practices. You will conduct rigorous code reviews for internal and vendor-delivered artifacts, maintaining a standardized, world-class global code repository.
- Implement Guardrails: Build human-in-the-loop (HITL) overrides and strict operational guardrails into agent architectures to eliminate catastrophic hallucinations and prevent infinite execution loops.
- Maintain Code Excellence: Write exceptionally clean, modular, and reusable Python/TypeScript code. Conduct rigorous code reviews for internal and vendor-delivered components to maintain a global standard.
- Stakeholder Translation: Act as a technical translator, clearly articulating complex AI concepts, loop mechanics, and architectural risks to non-technical business leaders and project teams.
What Experience You Need- Experience: 3+ years of professional experience building production-grade AI/ML applications, with a heavy emphasis on LLM orchestration and autonomous agent patterns over the last 1-2 years.
- Software Engineering Mastery: Strong proficiency in Python or TypeScript, with a deep understanding of asynchronous programming, API design, and microservices architecture.
- Agentic Frameworks: Proven, production-level experience building custom agentic runtime loops or utilizing graph-based orchestration frameworks like LangGraph or Google Agent Development Kits (ADK).
- RAG & Vector Infrastructure: Practical experience working with Advanced RAG pipelines, semantic search, and vector databases
- Structured Outputs: Mastery of JSON schema design and structured decoding techniques for bulletproof LLM tool-calling.
- Problem-Solving Mindset: A strong architectural intuition for breaking down ambiguous, multi-step human tasks into structured, programmatic agent prompts and loops.
What Could Set You Apart- Regulated Industry Background: Prior experience deploying AI or high-throughput software solutions within a highly secure or regulated industry.
- Live production experience: Experience with deploying live AI solutions with Agentic workflows or GenAI solutions
- UiPath & Intelligent Automation: A strong understanding of the UiPath ecosystem and experience bridging traditional RPA with generative AI models.
- A proactive, self-motivated mindset with a passion for driving AI adoption across an organization to fundamentally change the way people work.
- Demonstrated learning agility and a proactive approach to mastering new technologies.
This is a newly created position.
Primary Location:CAN-Toronto-5700 Yonge
Function:Function - Tech Dev and Client Services
Schedule:Full time
