AI Agent Engineer Canada; Toronto, Vancouver​/Hybrid , India; Bangalore​/Hybrid Fremont-California​/Hybrid

Join our AI engineering team to design and develop the next generation of agentic AI applications
. You will be responsible for building intelligent systems that can understand objectives, reason through tasks, interact with tools and external systems, and execute complex workflows with minimal human intervention.

The role combines advanced AI capabilities with strong software engineering practices, requiring you to take agentic solutions from experimentation to reliable, scalable production systems.

• Design, develop, and deploy production-ready AI agents and agentic workflows.
• Build systems that enable AI agents to reason, plan, make decisions, and execute multi-step tasks.
• Integrate LLMs with internal systems, databases, APIs, and external tools.
• Develop tool-calling and function-calling capabilities for AI agents.
• Build and optimize RAG pipelines for knowledge-grounded AI applications.
• Design multi-agent workflows and agent orchestration systems.
• Implement memory, context management, state management, and workflow persistence.
• Evaluate agent performance, accuracy, reliability, and safety.
• Develop evaluation and monitoring frameworks for production AI agents.
• Optimize agent applications for latency, scalability, reliability, and cost.
• Integrate AI agents with enterprise applications and business workflows.
• Implement appropriate guardrails, validation, security, and access controls.
• Collaborate with AI/ML, software, data, and product teams.
• Mentor junior engineers and contribute to technical architecture decisions.

• 5+ years of professional experience in AI/ML, software engineering, or a related field.
• Strong programming skills in Python
  .
• Strong understanding of LLMs, Generative AI, and AI application development
  .
• Hands-on experience building LLM-powered applications and agentic workflows.
• Experience with RAG, embeddings, vector databases, and semantic search
  .
• Experience working with LLM APIs and open-source models.
• Strong understanding of APIs, microservices, databases, and software engineering principles.
• Experience with agent frameworks such as Lang Graph, Lang Chain, Semantic Kernel
  , or similar technologies.
• Experience deploying AI applications in production or cloud environments.
• Familiarity with Docker, CI/CD, and AWS, Azure, or GCP.
• Understanding of prompt engineering, tool calling, structured outputs, and context management.
• Strong analytical, problem-solving, and communication skills.