Search
Go
Sr. AI Engineer (AI/ML Inference)
Summary by AIEngineer.careers
Sr. AI Engineer (AI/ML Inference) is a AI Infrastructure Engineer role (full-time). with Dialpad. in VANCOUVER, CA. Compensation shown: $136K–$158K (est.). Imported listing (source: zerogtalent.com). Apply on the employer's site (zerogtalent.com).
Imported listing (source: zerogtalent.com) · Apply on zerogtalent.com
VANCOUVER · CA
$136K–$158K (est.)
Full-time
SENIOR
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from zerogtalent.com
Senior AI Engineer specializing in systems and inference for Dialpad's Speech Team. You will productionize speech models, optimize self-hosted inference at scale, and build reliable, low-latency services for real-time voice agents. This role bridges ML infrastructure and backend engineering to ensure high availability and performance.
Responsibilities
- Own the productionization path from speech models/APIs to scalable, reliable services.
- Optimize self-hosted inference architecture for concurrency, latency, and cost efficiency.
- Integrate third-party speech APIs with robust failover and vendor-performance monitoring.
- Implement observability, alerting, and incident response practices to meet strict SLAs.
- Build release evaluation infrastructure including shadow traffic and staged rollouts.
- Mentor engineers and collaborate cross-functionally with MLOps and product teams.
Requirements
- Strong software engineering fundamentals with proficiency in Python.
- 5+ years of experience building production software, preferably in ML-backed or real-time systems.
- Hands-on experience deploying, scaling, and troubleshooting ML models in production.
Dialpad
San Ramon · US · 1400+ employees
Dialpad is an AI-powered communications intelligence platform that provides cloud-based support, contact center solutions, and sales outreach tools. The company focuses on transforming business communications by turning conversations into actionable intelligence to help teams automate workflows and enhance customer experiences.
