Sr. AI Engineer (AI/ML Inference)
Core
Build and operate production systems for real-time speech AI agents, enabling self-hosted inference, third-party API integration, and reliable service delivery for Dialpad's customer experience platform.
Role type
Senior IC backend engineer (AI/ML inference systems)
Builds
Scalable, low-latency speech inference services and operational infrastructure for AI voice agents
Domain
Telecommunications / AI / Speech Technology
Deliverable
production ML models | infrastructure
Required skills
Python, API design, production ML systems, model serving, cloud infrastructure, distributed systems, observability, incident response
Preferred skills
Experience with streaming media, GCP, containers, orchestration, CI/CD
Technologies
Python, GCP, containers, orchestration, CI/CD
Responsibilities
Own the path from speech model to production by building APIs, services, and deployment workflows; Optimize self-hosted speech model serving architecture for concurrency, autoscaling, and cost; Integrate and maintain third-party speech APIs with failover and capacity planning; Build monitoring, alerting, and incident-response practices to meet uptime and latency SLAs; Partner on release infrastructure including shadow traffic, staged rollouts, and versioning; Mentor engineers and set technical direction across speech, platform, and product teams
Seniority
Senior, hands-on IC