How Remoteville checks and expires listings
Software Engineer III, Voice AI
Skills
AdoptionContact CentersContinuous IntegrationDatabasesECSOkta Identity CloudPCM
What the job involves
The main requirements, responsibilities and hiring steps.
Requirements
- 5+ years of software development experience with scalable backend services using Node.js and TypeScript
- 1+ years of production experience with voice AI conversational AI or real-time audio systems
- Hands-on experience with agentic LLM architectures including tool calling multi-agent orchestration prompt engineering and conversation state management
- Familiarity with voice AI pipeline components such as STT TTS and LLM APIs
- Experience with telephony systems such as Twilio media streams SIP or IVR
- Understanding of voice-specific challenges including VAD turn-taking interruption handling latency budgets and audio codecs
- Solid understanding of SDLC including build configuration release and deployment
- Knowledge of microservice architecture and distributed systems best practices
- Proficiency with AWS services including ECS Fargate Lambda DynamoDB S3 Kafka MSK and API Gateway
- Experience with event-driven architecture and message processing such as Kafka or SQS
- Strong relational database skills with MySQL and exposure to DynamoDB or Redis
- Excellent teamwork communication and organizational skills
Nice to have
- Collaborative mindset
- Continuous learner
- Mentoring ability
- Detail oriented
- Patient focused
Day to day
- Design, develop, and maintain a real-time Voice AI platform that powers thousands of patient calls each day
- Build conversational systems using TypeScript and Node.js with STT, LLM orchestration, and TTS pipelines
- Optimize call quality and responsiveness by tuning VAD, turn-taking, interruption handling, and latency across audio streaming workflows
- Collaborate with product, QA, clinical operations, analytics, and engineering teams to ship reliable voice features and improve patient satisfaction