Staff AI/ML Engineer – Generative AI & Autonomous Agents (10035) Toronto, Canada - Hybrid

Key Responsibilities

• Design and implement the business logic and modeling that governs agent behavior, including decision-making workflows, tool usage, and interaction policies. 
• Develop and refine LLM-driven agents using prompt engineering, retrieval-augmented generation (RAG), fine-tuning, or function calling. 
• Understand and model the domain knowledge behind each agent: engage with network engineers, learn the operational context, and encode this understanding into effective agent behavior. 
• Apply traditional ML modeling techniques (classification, regression, clustering, anomaly detection) to enrich agent capabilities. 
• Contribute to the data engineering pipeline that feeds agents, including data extraction, transformation, and semantic chunking. 
• Build modular, reusable AI components and integrate them with backend APIs, vector stores, and network telemetry pipelines. 
• Collaborate with other AI engineers to create multi-agent workflows, including planning, refinement, execution, and escalation steps. 
• Translate GenAI prototypes into production-grade, scalable, and testable services in collaboration with platform and engineering teams. 
• Work with frontend developers to design agent experiences and contribute to UX interactions with human-in-the-loop feedback. 
• Stay up to date on trends in LLM architectures, agent frameworks, evaluation strategies, and GenAI standards. 

Qualifications

• Master’s or PhD in Computer Science, Artificial Intelligence, Machine Learning, or a related field. 
• 5+ years of experience in ML/AI engineering, including 2+ years working with transformer models or LLM systems. 
• Strong knowledge of ML fundamentals, with hands-on experience building and deploying traditional ML models. 
• Solid programming skills in Python, with experience integrating AI modules into cloud-native microservices. 
• Experience with LLM frameworks (e.g., LangChain, AutoGen, Semantic Kernel, Haystack), and vector databases (e.g., FAISS, Weaviate, Pinecone). 
• Familiarity with prompt engineering techniques for system design, memory management, instruction tuning, and tool-use chaining. 
• Strong understanding of RAG architectures, including semantic chunking, metadata design, and hybrid retrieval. 
• Hands-on experience with data preprocessing, ETL workflows, and embedding generation. 
• Proven ability to work with cloud platforms like AWS or Azure for model deployment, data storage, and orchestration. 
• Excellent collaboration and communication skills, including cross-functional work with product managers, network engineers, and backend teams. 

Nice to Have

• Experience with LLMOps tools, open-source agent frameworks, or orchestration libraries . 
• Familiarity with Docker, Docker Compose, and container-based development environments. 
• Background in enterprise networking, SD-WAN, or network observability tools. 
• Contributions to open-source AI or GenAI libraries.