Job Specifications
About Home.CA
We’re building Canada’s #1 Home Ecosystem, reimagining the end-to-end homeownership experience for millions of Canadians, making it simple and rewarding.
The Role
We're looking for an exceptionally passionate Senior Data Science Engineer who understands that world-class AI requires world-class data infrastructure. You want your work to directly impact how Canadians make critical housing decisions, not just by tuning models, but by mastering the ingestion, normalization, and delivery of complex, diverse data types. This isn't about working in a sandbox—this is about building the production data backbone that powers real-time, trustworthy insights for thousands of users daily.
Every pipeline you architect, every dataset you clean, and every model you deploy translates directly into better financial decisions, more informed homeowners, and improved quality of life. In our startup environment, your impact is immediate and unmediated—you aren't just maintaining a platform, you're defining the technical trajectory of the business. Your work will build the foundation of truth that Canadians trust for their most important asset.
What You'll Build
# Data Engineering & Pipeline Architecture
- Architect robust pipelines to ingest, normalize, and reconcile data from **PostgreSQL**, NoSQL databases, and diverse external sources
- Design schema unification strategies to harmonize disparate data types (financial data, market signals, property records)
- Build feature stores and data lakes that serve as the single source of truth for models and agents
- Implement rigorous data quality checks, validation frameworks, and anomaly detection
- Manage the evolution of data schemas and ensure consistency across the platform
# Semantic Data & RAG Systems
- Build embedding pipelines for multi-modal data
- Design and optimize **Vector Search** implementations for critical platform data
- Implement semantic search across numerous document categories
- Tune retrieval strategies for context-aware, user-specific information filtering
- Measure and improve RAG relevance metrics
# Personalization & Recommendation
- Develop user-specific property recommendations based on preferences, behavior, and context
- Build content recommendation systems for home improvement ideas, advisory articles, and expert profiles
- Design collaborative filtering and hybrid recommendation approaches
- Implement cold-start strategies for new users and properties
Your Profile
# Required Technical Depth
- **6+ years** production experience with data engineering and ML systems
- Expert-level knowledge of **data modeling**, **schema design**, and **ETL/ELT pipelines**
- Strong proficiency in **Python** and **SQL** for complex data manipulation and analysis
- Production experience with **RAG architectures**, vector databases, and semantic search
- Deep understanding of **embedding models** and unstructured data processing
- Solid software engineering skills: **TypeScript/Node.js** and API development
- Experience with NoSQL databases (Firestore, MongoDB), **PostgreSQL**, and distributed data systems
# Essential Qualities
- **Unwavering dedication**: You're driven by the knowledge that your work helps families make life-changing decisions
- **Data integrity obsession**: You care deeply about data quality, consistency, and truth
- **Production-first mentality**: You think about latency, fallbacks, cost, and monitoring—not just research metrics
- **Canadian context awareness**: Understanding of Canadian property ownership, regulations, and user needs
- **Passion for data excellence**: Excited about building the pristine data foundation that enables intelligent agents and generative AI
# Bonus Skills
- Knowledge of **Angular** or modern frontend frameworks for model integration
- Background in **NLP**, **information retrieval**, or **recommendation systems**
- Familiarity with **geospatial analysis** and location-based features
- Understanding of **Canadian privacy laws** and data governance
# Tech Stack You'll Work With
**ML/AI Platforms**: Vertex AI (Gemini, Vector Search, RAG Engine), LangChain, LangGraph
**Languages**: Python, TypeScript, SQL
**Data Storage**: Firestore, BigTable, BigQuery
**Backend Services**: Node.js, Spring Boot (Java)
**Vector Databases**: Vertex AI Vector Search, Pinecone, Weaviate
**APIs**: OpenAI, Anthropic, Google AI (Gemini)
**Infrastructure**: Google Cloud Platform, Docker, Kubernetes
**Monitoring**: Cloud Monitoring, custom evaluation dashboards
**Version Control**: Git
# What Makes This Role Exceptional
1. **Direct User Impact**: Your models power conversations—every model directly improves user value
2. **Cutting-Edge AI**: Work with production-grade AI/ML services including generative models and intelligent agents
3. **Data Richness**: Work with financial models, user behavior, neighborhood data, MLS listings, and transaction records
4. **End-to-End O