SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: CAD 185,000 - 220,000 / annual
Dutch is a veterinary telemedicine platform that enables pet parents to connect with licensed veterinarians for virtual visits, diagnosis, prescriptions, and medication delivery. The company is backed by top-tier investors including Forerunner Ventures, Eclipse Ventures, and Bling Capital, and is led by founders from successful startups like Hims and PlushCare.
You will be a hands-on Lead AI/Data Engineer responsible for building and scaling AI systems that power Dutch's platform. This role spans three primary areas:
**AI Services & Platform Tooling (60%):** Design, build, and operate production AI agents and services for pet parents, veterinarians, and internal teams. Own the AI development infrastructure including evaluation frameworks, prompt optimization, LLM observability, and cost management. Establish engineering standards and reusable patterns for retrieval, tool calling, guardrails, and model selection. Design and run systematic experiments across models, prompts, retrieval strategies, and agent architectures, building evaluation datasets and automated tests to measure quality, safety, performance, and cost. Evolve the semantic layer enabling AI systems to answer business questions accurately. Work closely with product engineering to deliver AI capabilities through APIs and integrate them into production applications.
**Data & Analytics Engineering (25%):** Build and maintain reliable ELT pipelines and dbt models in Snowflake using Prefect for orchestration and Fivetran/Airbyte for ingestion. Develop trusted data marts and datasets supporting AI features, product analytics, and experimentation. Build the data foundation for experimentation with consistent metrics and feature impact measurement. Maintain automated data quality tests, freshness checks, and alerts for critical pipelines. Diagnose pipeline failures and improve reliability. Support warehouse security, governance, performance, and cost management.
**Event Tracking & Product Analytics (15%):** Build and maintain reliable event data pipelines from Segment into Amplitude, Iterable, and Snowflake. Partner with product engineering to define event tracking plans for new features. Diagnose and resolve identity resolution and tracking issues affecting AI systems and analytics. Support product experimentation through reliable event tracking and accurate measurement. Build and maintain Amplitude dashboards helping product teams understand user behavior.
You will take ownership of technical decisions from architecture through deployment and ongoing operations, build reusable tools and frameworks that help teams ship AI capabilities faster, and use evaluations and data to guide continuous improvement.
**Requirements:**
- 6+ years of experience in software, data, or ML engineering, including 2+ years building and operating LLM applications in production
- Strong Python and SQL skills with experience building reliable, maintainable production systems
- Hands-on experience developing AI agents and applications using LLM APIs, agent frameworks, tool calling, retrieval, and structured outputs
- Experience designing and running LLM evaluations including test datasets, automated graders, regression testing, and systematic experimentation
- Experience with LLM observability, performance optimization, and cost management in production
- Experience deploying and operating services on AWS, GCP, or Azure using containers and CI/CD pipelines
- Working knowledge of modern data platforms including Snowflake or similar warehouses, dbt, and orchestration tools such as Prefect, Airflow, or Dagster
- Familiarity with product analytics and event tracking platforms such as Segment and Amplitude, or willingness to learn
- Familiarity with BI tools such as Sigma, Looker, or Tableau
- Bonus: Experience with prompt optimization, semantic layers, data contracts, or A/B testing and experimentation infrastructure
