Staff AI Engineer

Location: Toronto, Ontario

We are partnering with an established Canadian technology company seeking an experienced Staff AI Engineer to lead the architecture, development, and deployment of production-grade AI solutions.

This is a newly created position offering significant technical ownership and the opportunity to shape how AI is adopted across an established software platform.

The successful candidate will combine strong software engineering fundamentals with deep, hands-on experience in Generative AI, machine learning, document intelligence, and cloud-native architecture.

This is not a research-focused position. We are looking for an engineer who has successfully taken AI applications into production and understands the practical challenges of accuracy, reliability, scalability, performance, and cost.

What You'll Be Doing

AI Architecture & Technical Leadership:
- Lead the design and implementation of end-to-end AI systems integrated into existing software products.
- Evaluate commercial LLM APIs, specialized AI services, and open-source models to determine the best technical approach.
- Establish architectural standards for RAG, retrieval, model integration, evaluation, monitoring, and fallback strategies.
- Provide technical leadership and mentorship to engineers working across AI, data, and software platforms.
- Collaborate with engineering leadership and product stakeholders to establish AI development priorities and technical roadmaps.

Generative AI & Document Intelligence:
- Develop AI-powered solutions for extracting, interpreting, and structuring information from complex documents, including PDFs, technical documentation, tables, and drawings.
- Build intelligent search and matching capabilities using embeddings, vector databases, semantic retrieval, and reranking.
- Implement workflows combining OCR, multimodal models, structured outputs, and automated validation.
- Develop AI-assisted automation features that improve the accuracy and efficiency of existing business processes.

Evaluation, Reliability & Performance:
- Design evaluation frameworks using benchmark datasets, automated testing, regression analysis, and accuracy metrics.
- Establish confidence thresholds, validation processes, and human-review workflows for AI-generated outputs.
- Monitor production AI systems for performance degradation, model drift, and unexpected failures.
- Optimize inference costs, response times, API usage, caching, and scalability.
- Implement appropriate safeguards, error handling, and fallback mechanisms.

Production Engineering:
- Build and deploy AI-powered services within an AWS-based microservices environment.
- Integrate AI functionality with existing Node.js/TypeScript applications and REST APIs.
- Collaborate with software and DevOps engineers on containerization, CI/CD, monitoring, and deployment automation.
- Maintain high standards for software quality, maintainability, security, and system design.

Must Have Skills:

What We're Looking For

- 7+ years of professional software engineering experience, including 5+ years developing and deploying AI/ML systems in production.
- Advanced proficiency in Node.js and TypeScript, including backend architecture, API development, and integration.
- Strong hands-on experience with LLMs, Generative AI, RAG architectures, prompt engineering, structured outputs, and tool integration.
- Experience with vector databases and semantic retrieval technologies such as Pinecone, Qdrant, Weaviate, or pgvector.
- Experience evaluating and integrating commercial AI APIs, specialized AI services, and open-source models.
- Demonstrated experience building AI evaluation frameworks, including benchmark datasets, regression testing, and production monitoring.
- Experience processing complex, unstructured documents using OCR, multimodal LLMs, or document intelligence technologies.
- Strong AWS, Docker, microservices, and production deployment experience.
- Solid understanding of software architecture, design patterns, REST APIs, and relational databases such as PostgreSQL or MySQL.
- Ability to make informed architectural decisions balancing accuracy, scalability, latency, maintainability, and cost.
- Strong communication skills and experience collaborating with technical teams, product stakeholders, and senior leadership.

Nice to Have Skills:

- Experience with LangChain, LlamaIndex, or similar AI orchestration frameworks.
- Deep learning experience using PyTorch or TensorFlow.
- Experience fine-tuning embedding models or rerankers for specialized retrieval applications.
- Knowledge of traditional machine learning techniques such as regression, gradient boosting, or XGBoost.
- Experience with PHP-based applications or services.
- Experience building AI capabilities for enterprise SaaS, workflow automation, technical document processing, or data-intensive business applications.
- Previous experience mentoring engineers or providing technical leadership within a small team.