About the role
TL;DR
Lead AI Architect for a real-time voice copilot, transitioning from PoC to production.
- •Neurons Lab is seeking an AI Architect to lead the technical architecture and delivery of a real-time voice copilot for veterinary care coordinators.
- •This role transitions a validated PoC to production, focusing on latency, accuracy, concurrency, and cost.
- •Key Responsibilities Own the full voice copilot pipeline from streaming speech-to-text to AWS infrastructure.
- •Drive latency improvements and run model A/B tests for accuracy.
- •Manage evaluation, cost, and hardening for production environments.
- •Lead technical discussions with clients and transfer knowledge to internal teams.
- •Requirements Mandatory production Voice AI experience with real-time voice or speech products. 6+ years of hands-on AI/ML engineering with recent LLM production practice.
- •Proven record in latency reduction and concurrency fixes on live systems.
- •Consulting/client-facing seniority with calm and precise communication.
Required skills
PythonTypeScriptAWSLLMsOpenAI APIAnthropic APILangChainNLPAWS LambdaCI/CDDockerKubernetesGitLinux
Nice-to-have skills
React
Domain expertise
healthcare
Tech stack
PythonTypeScriptAWSLLMs