Agentic AI Engineer

Job# FT30660
Location Toronto, ON
Job Type Contract
Salary Negotiable
Contact [email protected]
Status EXPIRED
Date Posted October 28, 2025
Submission Deadline November 07, 2025
Job Stream
Benefits 3 Month contract to start

Details

Job Description :Our client is looking for a Agentic AI Engineer in Toronto, ON

Must Have Primary Skills :
Overview:
 Client are seeking a hands-on Agentic AI Platform Engineer with deep experience in Python, Generative AI frameworks, and containerized deployments on Kubernetes (OCP, Azure, AWS). This is a 100% coding role, focused on designing, developing, and deploying production-grade AI platform components — from LLM orchestration to secure, scalable, multi-agent systems.


Nice To Have Secondary Skills :
  • Design, code, and deploy Python-based microservices and frameworks enabling orchestration of LLM-driven agents. 
  • Build and maintain containerized AI workloadsusing Docker and Kubernetes (OpenShift, EKS, AKS). 
  • Develop APIs, SDKs, and Python libraries that power GenAI and agentic workloads across RBC business lines. 
  • Implement end-to-end orchestration for agent workflows, integrating frameworks such as LangChain, Semantic Kernel, or Haystack.
  • Integrate and operationalize MCP-Context-Forge for context management, orchestration, and inter-agent communication.
  • Embed observability, monitoring, and governance into all platform services (Prometheus, Grafana, OpenTelemetry). 
  • Ensure secure and compliant AI operationsthrough Kubernetes-native policies, RBAC, and network isolation. 
  • Collaborate closely with data scientists, AI researchers, and DevOps teams to productionize models and agent workflows. 
  • Prototype, benchmark, and deploy LLM pipelines on multi-cloud environments (OCP, Azure, AWS). 
  • Continuously enhance developer experience by contributing to internal Python SDKs, deployment automation, and CI/CD pipelines.


Proven Experience In :
Required Qualifications :
  • Expert-level Python developer — strong track record of building frameworks, SDKs, or orchestration systems. 
  • Hands-on experience coding and deploying GenAI / LLM-powered applications using LangChain, Semantic Kernel, or custom agent frameworks. 
  • Deep expertise in containerization and Kubernetes:  
  • Proficient in Docker, Helm, and Kubernetes manifests (Deployments, Services, ConfigMaps, Secrets). 
  • Experienced with OpenShift (OCP), Azure AKS, and/or AWS EKS for production-grade deployments. 
  • Familiar with Kubernetes networking, security (RBAC, NetworkPolicies), and monitoring. 
  • Strong understanding of CI/CD pipelines and automation tools such as GitHub Actions, ArgoCD, or Jenkins. 
  • Familiarity with observability stacks(Prometheus, Grafana, Loki, OpenTelemetry). 
  • Hands-on experience with microservices design, API development, and event-driven orchestration. 
  • Solid understanding of LLM system design, context management, and retrieval-augmented generation (RAG) architectures.
  • Comfortable working across hybrid and multi-cloud environments with secure service connectivity.
Preferred Qualifications: 
  • Experience developing Python SDKs, internal APIs, or developer tools for enterprise platforms. 
  • Familiarity with model serving frameworks(KServe, Ray Serve, BentoML) and distributed AI orchestration. 
  • Knowledge of service mesh architectures(Istio, Linkerd) and policy enforcement in Kubernetes. 
  • Experience integrating MCP-Context-Forge or similar orchestration technologies. 
  • Background in financial services, particularly in secure AI deployment or regulated environments.
 IND1
Please send your resume to [email protected]
Skills
  • Databases
    • Experience In at least 8 years of experience with/in Python, PySpark
  • Software
    • Experience In at least 6 years of experience with/in Generative AI
Industry experience required: Banking