Staff / Principal Software Engineer - Canada
Remote • Vancouver, British Columbia, Canada • FullTime
Posted 1y ago
About the job
Inworld is seeking an ambitious and capable Staff/Principal Backend Engineer to join their team and contribute to the advancement of the Inworld AI platform. This role will involve working on exciting new products, including the Inworld Router, an intelligent routing layer for LLMs, and API-based model services for TTS/STT. You will tackle complex infrastructural projects, focusing on platformization, development tools, and system-wide billing. The position emphasizes rapid iteration, building novel platform capabilities, and optimizing for real-time performance in consumer AI applications. Collaboration with ML teams is integral to the role, as AI and ML are critical to the platform's vision.
Responsibilities
- Own core systems for multi-provider failover, cost/latency-based routing, A/B experimentation, and real-time observability at massive scale for the Inworld Router.
- Develop and maintain API-based model services, including TTS, STT, LLM, and RAG capabilities.
- Contribute to new, ambitious, and large-scale product launches.
- Develop services for control and optimization of AI capabilities.
- Work on complex infrastructural projects such as platformization of new offerings and system-wide billing.
- Collaborate with Product Managers, engineers, and leads to define and focus on key product needs.
- Operate with technical autonomy, suggesting and implementing technical solutions and standards.
- Collaborate with peers to execute and deliver on projects, optimizing for both speed and quality.
- Advocate for and implement system improvements, both feature-related and independent.
Requirements
- Excellent programming skills in a statically typed backend language (preferably Go, Python, C++, or Rust).
- Experience developing and deploying cloud-based services handling hundreds of queries per second.
- Hands-on experience with relational databases (PostgreSQL or MySQL).
- Experience with caching (Redis or Memcached), pub/sub queues, data pipelines (Flink, Beam), and cloud storage.
- Excellent verbal and written communication skills, with the ability to collaborate effectively.
- Experience building API gateways, routing/proxy layers, or multi-provider orchestration systems (bonus).
- Experience with analytics or timeseries databases (ClickHouse, Timescale, InfluxDB) (bonus).
- Experience with OpenTelemetry (bonus).
- Experience with C++ (bonus).
Benefits
- Equity
- Health insurance
- Paid time off