We are seeking an AI Engineer with expertise in Generative AI, voice calling systems, conversational AI, and AWS. You will be responsible for building and optimizing our nationwide AI-powered voice calling products.
This role combines Gen AI expertise with deep AI/ML development (speech + LLMs) to deliver highly reliable, low-latency, real-time voice systems. You will work closely with the Solutions Architect to ensure scalable design.
Key ResponsibilitiesVoice AI Development
Build end-to-end pipelines for real-time calls
Integrate 3rd party voice calling/receiving services (e.g., Twilio)
Integrate LLMs (OpenAI, Anthropic, Llama, etc.)
Ensure natural, multi-language voice delivery
Generative AI Solutions
Implement RAG pipelines with vector databases for contextual conversations
Apply prompt engineering to improve conversational quality
Ensure compliance, safety, and bias mitigation in AI responses
AWS & Deployment
Deploy and scale AI workloads on AWS (EKS, Lambda, EC2, S3, DynamoDB, etc.)
Optimize GPU/compute workloads for low-latency inference
Collaborate with Solutions Architect on API contracts & integration patterns
4+ years in AI/ML engineering (focus on conversational AI, voice, or telephony)
Hands-on experience integrating STT, TTS, and LLMs into production systems
Strong knowledge of AWS services for AI/voice deployments
Skilled in Python/Node.js and AI frameworks
Experience building real-time/low-latency applications
Experience with multilingual systems (especially low-resource languages)
Prior work on AI-powered contact center or telephony platforms
Knowledge of AI compliance in telecom (GDPR, HIPAA, etc.)