This is a flexible position and has the option of working in our Toronto office full time, hybrid throughout the week or working entirely remotely within Canada.
The Staff Agentic Developer is responsible for driving engineering execution on the runtime that powers Vena AI - the substrate that runs agents reliably, efficiently, and at scale. Reporting to the Senior Director, this role provides strong technical expertise across agent orchestration, platform engineering, and delivery of Vena AI’s agentic capabilities. The role serves as a senior technical contributor and subject matter expert within the Vena AI team, working in alignment with the approaches and technology established by the Principal Agentic Developer.
How You'll Make an Impact
- Lead development of agent runtime and multi-agent orchestration components - the substrate every capability runs on.
- Contribute to architecture design and technical decision-making for the agent platform and its integration with the orchestration layer.
- Build scalable services, workflows, and orchestration primitives (fan-out, verify, synthesize, loop-until-done) supporting agentic AI experiences.
- Build secure agent execution controls - tool permissions, credential scoping, data-access boundaries, and guardrails - that protect customer financial data.
- Implement and operate model-routing and inference infrastructure with Azure Foundry, improving cost, latency, and reliability.
- Partner with Infrastructure Teams and Platform Engineering to deliver customer-facing capabilities.
- Drive engineering quality through code reviews, agent evaluation frameworks and CI quality gates that block regressions before release, testing, and development best practices.
- Support platform scalability, reliability, and performance across agent execution, including end-to-end tracing, latency profiling, and per-tenant token and cost attribution.
- Mentor engineers and apply the orchestration patterns and agent-reliability standards the team builds on.
- Contribute to integrating Vena AI capabilities across the broader Vena platform.
- Other duties, as assigned.
We'd Love to See
- 8+ years of software engineering experience with a strong track record delivering enterprise software solutions.
- Strong expertise in distributed systems and async/concurrent architectures (e.g., Python asyncio, Go), and hands-on experience building agent or orchestration frameworks - not just consuming AI APIs.
- Experience building cloud-native, data-intensive, or AI-enabled applications at scale.
- Proven experience with production LLM systems - model routing, inference cost/latency optimization, reliability, and observability.
- Experience with autonomous or multi-agent systems in production (a strong plus).
- Experience working in fast-paced, high-growth technology environments.
- Strong problem-solving and analytical capabilities.
- Commitment to engineering quality, maintainability, and operational excellence.
- Excellent collaboration and communication skills.
- Fluency using AI coding agents in your own engineering workflow, with the judgment to verify their output and stay accountable for what ships.
- Passion for continuous learning and technical innovation.
Preferred Qualifications
- Hands-on experience with agent protocols and frameworks such as MCP, A2A, LangGraph, or Semantic Kernel.
- Experience with durable workflow orchestration engines (e.g., Temporal, Azure Durable Functions) for long-running agent tasks.
- Experience with Microsoft Foundry (formerly Azure AI Foundry), Azure OpenAI, and related Azure services.
- Familiarity with LLM evaluation methods (LLM-as-judge, regression suites, red-teaming) and AI observability tooling (e.g., OpenTelemetry).
Base salary range 209,547 - 283,506 CAD
*Our salaries are tailored to roles, levels and locations. Your individual pay within this range is influenced by factors like work location, skills, experience and education. As you progress in your role, your compensation may adapt, offering flexibility for growth beyond initial levels. For specifics, your recruiter will provide details and address any questions during the hiring process.