Join a forward-thinking team focused on transforming complex business challenges into efficient, AI-powered solutions. As an AI Automation Engineer, you'll play a central role in developing systems that process unstructured data, extract meaningful insights, and automate critical workflows across enterprise functions.
What You’ll Do
- Design and deploy AI-driven automation pipelines using Python with FastAPI, LangChain, and spaCy, or Node.js with LLM API integrations and task automation frameworks.
- Develop and refine OCR systems to extract data from invoices, receipts, and other document types, combining semantic search with rule-based logic for accurate classification.
- Create intelligent agents that perform reconciliation, tagging, and anomaly detection across financial and operational datasets.
- Adapt and manage large language models for tasks like document summarization, entity extraction, and workflow alignment based on contextual understanding.
- Deploy inference systems at scale using cloud platforms such as GCP Vertex AI and AWS Lambda, or through containerized microservices with Docker and Kubernetes.
- Integrate AI outputs into practical tools like dashboards and APIs to support real-world decision-making and user adoption.
- Monitor model behavior and trigger retraining when performance declines or data patterns shift, using automated evaluation frameworks.
- Work closely with data, DevOps, and product teams to ensure solutions meet both technical standards and business objectives, including compliance requirements.
What We’re Looking For
- Degree in Computer Science, Data Science, or a related discipline.
- Strong coding skills in Python or Node.js, with direct experience in FastAPI, LangChain, or spaCy.
- Proven understanding of NLP, OCR, semantic search, and automation powered by large language models.
- Hands-on deployment experience with AWS, GCP, or containerized environments using Docker and Kubernetes.
- Familiarity with vector databases such as Pinecone, FAISS, or Weaviate, and experience with prompt orchestration tools.
- Ability to solve complex problems and turn business needs into robust, scalable technical implementations.
Nice to Have
- Experience with MLOps practices, Vertex AI Pipelines, or AWS SageMaker.
- Background in financial data or document-heavy automation systems.
- Knowledge of data drift detection, retraining workflows, and evaluation metrics for LLMs.
Technology Environment
Python, Node.js, FastAPI, LangChain, spaCy, OCR, NLP, LLMs, AWS, GCP, Docker, Kubernetes, Vertex AI, AWS Lambda, Pinecone, FAISS, Weaviate, prompt orchestration frameworks
Work Environment
This role follows a hybrid model requiring four days per week in our downtown Toronto office, combining in-person collaboration with structured flexibility. You'll work in a supportive, inclusive culture that values diverse perspectives and practical innovation.
Benefits
- Full coverage of health, dental, and vision insurance for employees and dependents from day one.
- Hybrid work model with consistent in-office presence.
- Access to learning and development resources to support continuous growth.
Compensation
Annual salary range: $80,000 – $120,000 CAD
Our Commitment
We believe diverse teams drive better outcomes. We welcome applicants of all backgrounds, including differences in ethnicity, religion, disability, gender identity, sexual orientation, family status, age, and nationality. Accommodations are available throughout the hiring process—just let us know how we can support you.
