Senior AI Engineer – Agentic AI Platform, LLM & GraphRAG

Senior AI Engineer

Location: Toronto, ON | Hybrid (3 days onsite: Tuesday-Thursday, 8:30 AM to 5:00 PM)

We are seeking an experienced and highly motivated Senior AI Engineer to join the Technology Strategy team supporting transformative AI initiatives. This role is focused on designing, building, and operating advanced AI systems that enable end-to-end customer experiences, increase automation and straight-through processing, and accelerate digital transformation objectives.

The ideal candidate brings deep expertise in agentic AI systems, knowledge graphs, AI-powered document generation, cloud infrastructure, AI services, CI/CD, observability, and enterprise-scale deployments. You will partner closely with business and engineering stakeholders to deliver AI solutions that are accurate, explainable, secure, scalable, and production-ready.

This is a unique opportunity to help shape the future of AI-driven business transformation while working with cutting-edge technologies and modern AI architectures.

Key Responsibilities:
Design and Build Agentic AI Workflows
Architect and develop long-running, multi-stage AI-driven analytical workflows that can pause, resume, recover, and maintain state throughout execution.
Orchestrate large language models (LLMs) alongside tools for retrieval, reasoning, calculations, business rules, and structured data extraction.
Develop robust prompt engineering strategies and structured output frameworks to ensure validated, machine-consumable responses.
Build solutions on event-driven and event-sourced architectures, ensuring decisions, evidence, workflow states, and results are persisted throughout the process.
Deliver transparent and traceable AI workflows that provide explainability and auditability.

Build and Operate Enterprise Knowledge Graphs Design, implement, and maintain knowledge graph solutions using technologies such as Neo4j, MongoDB Atlas, or similar platforms.
Develop ingestion, extraction, and transformation pipelines that convert unstructured documents into validated and searchable knowledge models.
Ensure all extracted data includes provenance and source attribution.
Implement GraphRAG, vector search, embeddings, and hybrid retrieval strategies to provide grounded and evidence-based AI responses.
Optimize graph architecture for performance, scalability, and business usability.

Develop Open Agent Interfaces and AI Integrations Build Model Context Protocol (MCP) tool servers and Agent-to-Agent (A2A) interfaces that allow AI capabilities to be consumed by external systems and multi-agent ecosystems.
Integrate AI services with Microsoft Copilot Studio, low-code platforms, and conversational AI solutions.
Design conversational interfaces that leverage grounded enterprise knowledge while maintaining response accuracy and trustworthiness.
Enable business users to query enterprise knowledge assets and trigger analytical workflows through natural language interactions.

Establish AI Governance, Evaluation, and Safety Standards Implement comprehensive anti-hallucination controls to ensure all AI-generated outputs are sourced, validated, and explainable.
Build evaluation frameworks including regression testing, section-level scoring, edge-case validation, and human-review workflows.
Create measurable acceptance criteria and quality standards for AI solutions.
Implement guardrails for prompt injection protection, secure data handling, privacy compliance, and safe output generation.
Partner with governance and risk teams to produce documentation and evidence required for AI model reviews and compliance processes.

Productionize and Manage AI Platforms
Own end-to-end deployment processes from development through production.
Develop and maintain CI/CD pipelines, infrastructure automation, environment configuration, secrets management, and access controls.
Manage integrations with cloud-based AI services including:
- Foundation and hosted models
- Search and retrieval services
- Document repositories
- OCR and document intelligence platforms
- Vector databases and knowledge graph solutions Establish comprehensive observability practices, including logging, monitoring, distributed tracing, alerting, and operational analytics.
Drive reliability, scalability, and operational excellence across AI platforms and services.

Required Qualifications
Bachelor's or Master's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related field.
7+ years of software engineering experience with at least 3+ years focused on AI/ML solutions.
Strong expertise in building and deploying LLM-powered applications and agentic AI systems.
Experience designing and implementing knowledge graphs, GraphRAG architectures, vector databases, and retrieval-augmented generation solutions.
Hands-on experience with modern AI frameworks and orchestration tools.
Strong knowledge of cloud platforms such as Azure, AWS, or Google Cloud.
Experience building APIs, agent interfaces, and distributed systems.
Expertise with CI/CD pipelines, containerization, infrastructure automation, and DevOps practices.
Strong understanding of observability, monitoring, logging, and production support.
Experience implementing AI governance, evaluation methodologies, and responsible AI practices.
Excellent communication and stakeholder management skills.

Preferred Qualifications
Experience with Akka SDK or other event-sourced architectures.
Experience with Neo4j, MongoDB Atlas, GraphRAG, vector search, and embeddings.
Knowledge of Model Context Protocol (MCP) and Agent-to-Agent (A2A) frameworks.
Experience with Microsoft Copilot Studio or conversational AI platforms.
Familiarity with enterprise AI governance and regulatory compliance requirements.
Experience working in financial services, insurance, or highly regulated industries.

Job Id: PnpUj1A3vshGvkPsmB2iYoWVL7tSLI6fRt23/jpZJDbRh9NLSmQhLdwBnQBcCUMK4D9ELuRtbvaiKZ5vky793eJOFdGlQAeXiA==