Principal AI Engineer, Distributed Systems & Intelligent Platforms
$220,000–$220,000 year
RemoteCanada
Job Summary
Build and own backend services in Python and Node.js, architect serverless compute layers, and develop APIs that tie frontend experiences to underlying data and logic. Orchestrate sophisticated workflow engines using state machines, asynchronous event pipelines, and reliable retry patterns across distributed services. Design RESTful interfaces, integrate third-party systems, and leverage advanced NoSQL data modeling techniques to maintain performance under load. Monitor, debug, and continuously improve system observability and deployment reliability on cloud-native infrastructure when production issues arise. Collaborate across time zones, contribute to code reviews, and take end-to-end ownership of features on an AI-native learning platform.
Required Qualifications
- At least 6 years of experience building production software professionally
- Deep hands-on experience with Python and Node.js
- AWS production experience: Lambda, DynamoDB, S3, SQS, EventBridge, Step Functions
- Advanced NoSQL data modeling; composite key design, transactional writes, scalable single-table patterns
- LLM engineering experience: tool/function calling, prompt construction, multi-agent coordination, vector search, embedding pipelines, retrieval-augmented generation (RAG)
- Full-stack development capability with frontend integration experience
- Strong unit testing discipline and maintainable test strategies
- Container-based deployment experience (Docker)
- Solid RESTful API design fundamentals
Desired Qualifications
- Ability to reason about system-wide impact before writing a line of code, including downstream effects across services and data layers
- Track record of catching requirement gaps and design holes before they reach development
- Hands-on experience with Langfuse, synthetic AI pipeline testing, or token cost optimization strategies
- Step Functions applied specifically to AI workflow orchestration
- Reasoning effort configuration for LLM-based systems
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.