The team is small and builds systems that simulate, analyze and evaluate conversational agents, including voice and multimodal ones.
You will take work from start to finish, building scalable infrastructure and tools that help make AI agents safer, more reliable and closer to what people actually intend.
Responsibilities
Design and build systems for simulating, analyzing and evaluating conversational AI.
Build resilient AWS infrastructure that handles high-volume, real-time conversations, using tools such as Lambda, EC2, WebSockets and SIP.
Create algorithms and pipelines that uncover insights, spot failure modes and track agent reliability and safety.
Drive technical projects from architecture through delivery across backend, AI, voice and observability systems.
Work on-site with customers to build, sell, deploy and support the product.
Requirements
At least 1 year of hands-on experience building or delivering software systems in a technical role.
Working knowledge across databases, AWS infrastructure and AI engineering.
Hands-on experience with Python, FastAPI, Supabase, Redis, AWS and WebSockets.
Experience with voice AI tools such as LiveKit, Deepgram or similar platforms, plus familiarity with machine learning or LLMs.
Experience building algorithms or pipelines that analyze, evaluate or monitor AI systems or conversational agents.
Experience designing scalable real-time systems, owning technical projects from start to finish, and working directly with customers or end users.
Strong computer science fundamentals, shown through education or work experience. Experience with high-traffic systems or research is a plus.
Conditions
Base salary is $160,000 to $220,000 per year.
Visa sponsorship is not available.
The role is on-site in San Francisco, California, United States.