Staff Software Engineer - Agentic AI - Toronto $140,000 - $175,000 + 15% bonus (3 x days per week)
We’re working with a global technology organisation that is investing heavily in AI, agentic systems and intelligent products. The team is building next-generation AI capabilities that support professionals working in highly complex, information-rich and regulated environments.
This is a hands-on Staff-level engineering role sitting at the intersection of AI engineering, platform engineering and applied AI. You’ll be working on systems where accuracy, reliability, evaluation and governance genuinely matter — rather than simply building another chatbot.
You’ll help design, build and scale production-grade AI systems, with opportunities to contribute across areas including:
- Agentic AI and multi-step workflows
- AI-powered ingestion and data pipelines
- Search, retrieval and RAG systems
- AI platform and infrastructure
- Distributed systems and storage
- Evaluation, monitoring and observability
- Cloud-native AI applications
- AI governance, reliability and lifecycle management
You’ll have the opportunity to work across different layers of the platform depending on your experience — from the underlying infrastructure and ingestion pipelines through to search and the agentic layer.
A key part of the role is bridging the gap between AI research and practical engineering: understanding what modern AI can do, but knowing how to build, deploy, monitor and continuously improve those capabilities in production.
What You’ll Be Doing
- Architect and develop scalable, production-grade AI systems and platforms.
- Build and integrate agentic AI solutions capable of executing complex, multi-step workflows.
- Develop AI-powered applications using LLMs, RAG and retrieval technologies.
- Build cloud-native infrastructure and distributed systems supporting AI workloads.
- Design ingestion, storage, search and data-processing pipelines at scale.
- Develop and implement AI evaluation frameworks, metrics and quality processes.
- Establish monitoring, observability and operational practices for AI systems.
- Work closely with product, engineering and subject-matter experts to translate complex requirements into technical solutions.
- Evaluate emerging AI technologies and determine where they can deliver genuine value.
- Make architectural decisions across scalability, reliability, cost, performance and accuracy.
- Provide technical leadership and mentorship to other engineers.
You’ll ideally bring:
- Strong professional experience building and deploying AI-powered applications.
- Experience designing and building agentic AI systems or AI workflows.
- Strong Python engineering skills.
- Experience taking AI solutions into production cloud environments.
- Hands-on experience with technologies such as LangGraph, LangFuse, Kubernetes and Docker.
- Experience with AI evaluation, monitoring and observability.
- Solid understanding of distributed systems and software engineering fundamentals.
- Experience with RAG, semantic search, embeddings or information retrieval.
- Familiarity with modern AI/ML frameworks such as PyTorch is beneficial.
- Experience working with cloud platforms — AWS preferred, but cloud-agnostic experience is absolutely relevant.
- Strong understanding of data structures, algorithms and core computer science principles.
- The ability to make sound technical decisions and explain the trade-offs behind them.
- Experience operating at Senior, Lead or Staff level, with significant technical ownership.
GET