Quick overview
Job description
About the Role
Join a small AI team building systems to simulate, analyze, and evaluate conversational agents across voice and multimodal experiences. You will own technical work from architecture through deployment, helping improve the safety, reliability, and performance of real-time AI systems.
What You'll Do
Architect and build simulation, analysis, and evaluation systems for conversational AI.
Develop resilient AWS infrastructure for high-volume, real-time conversations using services and protocols such as Lambda, EC2, WebSockets, and SIP.
Build algorithms and pipelines that surface insights, detect failure modes, and support safe, reliable agent behavior.
Own end-to-end technical execution across backend, AI, voice, and observability systems.
Work on-site with customers to build, sell, deploy, and support the product.
What We're Looking For
At least one year in a technical role building or delivering software systems.
Full-stack proficiency across databases, AWS infrastructure, and AI engineering.
Experience with Python, FastAPI, Supabase, Redis, AWS, and WebSockets.
Familiarity with voice AI tools such as LiveKit, Deepgram, or comparable platforms.
Experience with machine learning, LLMs, and pipelines for analyzing, evaluating, or monitoring AI systems or conversational agents.
Experience designing scalable infrastructure for real-time systems or high concurrency, and owning technical execution from architecture through delivery.
Experience working directly with customers or end users; strong technical fundamentals, high-traffic systems experience, or research project experience are also valued.
Compensation & Benefits
Base salary: $160,000 to $220,000 annually. Visa sponsorship is not available.
Location
On-site in San Francisco, California, United States.