Staff AI Engineer

Salary: $100,000 - 205,000 per year Requirements: We want 7+ years of software engineering experience, including 5+ years building and deploying AI/ML systems in production. We need deep hands-on experience with LLMs, RAG architectures, prompt engineering, structured outputs, tool use, and vector databases such as Pinecone, Qdrant, Weaviate, or pgvector. We look for a proven record of choosing between vendor APIs, specialized document AI services, and self-hosted open-source models based on evidence, while managing production cost and latency trade-offs. We expect experience building evaluation layers, including golden datasets, regression suites, accuracy targets, and drift monitoring. We value fluency with common design patterns and the judgment to know when not to use them, along with experience refactoring REST APIs without breaking consumers. We want demonstrated ability to move AI systems from notebook prototypes to scalable, monitored microservices using Docker and AWS. We look for experience parsing complex unstructured documents such as PDFs, CAD/BIM tables, and drawings using OCR, multi-modal LLMs, or layout-aware models. We expect strong computer science fundamentals, system design expertise, clean coding practices, and solid SQL skills with PostgreSQL or MySQL. We need advanced skill in Node.js/TypeScript or Python. Nice-to-have experience includes AEC, PropTech, CPQ, supply chain, or technical e-commerce domain knowledge. Nice-to-have experience also includes PHP and REST API work, deep learning with PyTorch or TensorFlow, traditional ML methods, user-facing AI features requiring high accuracy and explainability, and mentoring or leading a small engineering team. Responsibilities: We will have you architect and deploy end-to-end AI pipelines for construction technical documents, submittals, schedules, and product cross-referencing. We will rely on you to make and defend build-versus-buy decisions for each capability using benchmarks for accuracy, latency, and cost per document. We expect you to define and uphold design standards for retrieval and RAG patterns, prompt and schema conventions, evaluation, production monitoring, and provider routing and fallback logic. You will serve as a senior technical authority, mentoring engineers and guiding technical decisions across our data and AI platforms. You will also identify when a deterministic approach is better than AI and make that case to product and executive stakeholders. We will have you build document intelligence pipelines for technical spec sheets, MEP blueprints, equipment schedules, and quotes using OCR, multi-modal models, schema-constrained outputs, validation, and confidence scoring. You will develop semantic search, embeddings, and reranking systems to match manufacturer products and part numbers automatically. You will help build retrieval and generative workflows within AutoQuote to speed up quoting and improve accuracy, with human review for low-confidence outputs. You will own the evaluation strategy for every AI feature, including golden datasets, regression testing, and release gating for model or prompt changes. You will set accuracy thresholds with Product and define human review routing and fallback behavior when performance falls below target. You will create tooling and benchmarks to compare models and providers using ATSs own documents. You will monitor production output for drift and failure patterns and help enforce data governance, quality, and privacy standards. You will integrate AI services into our AWS cloud microservices architecture with a focus on availability, latency, and cost efficiency. You will own unit economics such as cost per document and per quote, token usage, caching, batching, and vendor rate-limit and failure considerations. You will implement guardrails, retries, fallback paths, and continuous learning loops that feed reviewed output back into evaluation data. You will collaborate with software and DevOps teams to deliver CI/CD for AI features, with evaluation runs required before deployment. You will partner with Product Managers and executive stakeholders to assess feasibility, estimate impact, and shape technical roadmaps for AI initiatives. Technologies: AI API AWS Architect BIM CI/CD Cloud DevOps Docker MySQL PHP PostgreSQL PyTorch Python RAG REST SQL TensorFlow TypeScript microservices NodeJS Embedding Models Fine-tuning HTTP LLM MLOps Spark Web More: ATS Software is a dynamic, industrious, innovative, and collaborative company based in Scarborough, Toronto, with this role working in person. We are a new-position employer offering career advancement opportunities, a benefits package for eligible full-time employees that includes medical, vision, and dental coverage, and a culture that supports a healthy work-life balance. Our workplace also includes free parking, foosball, ping pong, a basketball net, gym facilities, and year-round employee events. The role reports to our Director of Technology, and the compensation range is CAD $100,000 to $205,000 plus benefits. last updated 41 week of 2026