Voice AI Engineer (Real-Time Speech)
Core
Design, build, and operationalize end-to-end real-time STT → LLM → TTS voicebot pipelines on AWS for a telecommunications company's customer care operations.
Role type
Senior IC Voice AI Engineer (Real-Time Speech)
Builds
Low-latency customer care Voicebot and Agentic Chatbot
Domain
Telecommunications / Real-Time Conversational AI
Deliverable
production ML models
Required skills
Real-time STT/TTS pipeline engineering, Amazon SageMaker GPU inference, Amazon Bedrock, NVIDIA GPU optimization, Kubernetes/EKS, Python, Redis, FPE tokenization, telephony platform integration (Avaya/Genesys)
Preferred skills
AWS Certified Machine Learning – Specialty, EMR-on-EKS, Apache Iceberg, MSK
Technologies
AWS (SageMaker, Bedrock, EKS, Redis, CloudWatch, Splunk, Terraform/CDK), NVIDIA A100/L40S, Python, GitLab CI/CD, MLflow, Avaya, Genesys
Responsibilities
Deploy and maintain production customer-trained Whisper and TTS models as low-latency real-time endpoints; Implement Bedrock Proxy Gateway for multi-model routing and high-availability serving; Integrate voicebot decision engines with core enterprise telephony and CVM platforms; Establish LLMOps & MLOps pipelines for experiment tracking and model versioning; Enforce data sovereignty by integrating FPE and tokenization wrappers into ML pipelines; Automate ML deployment workflows using GitLab CI/CD and IaC.
Seniority
Senior, hands-on IC
