Lead AI Engineer

Job Description

About Us

We're building the next generation of AI-powered business software. Our Voice AI application brings real-time conversational intelligence directly into customer and business workflows, combining low-latency speech pipelines with LLM-powered reasoning to get real work done through natural voice conversation.

This is a chance to work on hard problems in real-time voice systems, speech-to-text and text-to-speech pipelines, and conversational AI orchestration, building zero-to-one, scaling one-to-ten, owning your area end-to-end, and shipping to production at scale.

About the Role

We're looking for a Lead Voice AI Engineer to help build and scale our Voice AI application from the ground up. This is a hands-on, high-ownership role for someone who wants to be part of the full 0-1 and 1-10 journey — architecting core voice infrastructure early, then scaling it as usage grows. You'll work across the full voice stack in Python — STT, LLM, TTS, and ASR — built on the LiveKit framework, designing systems that feel natural, fast, and reliable in real-time conversation.

What You'll Do

• Design, build, and scale real-time voice AI pipelines in Python using STT, TTS, ASR, and LLM components on the LiveKit framework
• Optimize for low-latency, high-reliability voice interactions, tuning the pipeline across speech recognition, language understanding, and speech synthesis
• Drive technical decisions on system architecture, reliability, performance, and scalability for real-time conversational workloads
• Lead by example — set engineering standards, review designs and code, and mentor engineers on the team
• Collaborate closely with product, design, and AI/ML teams to translate business requirements into shipped functionality
• Work directly with customers to understand real-world use cases, troubleshoot issues, and gather feedback to inform the roadmap
• Continuously improve conversational quality, latency, and voice interaction accuracy as the product scales

What We're Looking For

• 4–6 years of software engineering experience, with strong, hands-on expertise in Python
• Practical experience building voice AI systems using STT, TTS, ASR, and LLM components, ideally with the LiveKit framework or similar real-time frameworks
• Demonstrated experience operating systems at decent scale — designing for real-time performance, reliability, and growing usage
• Solid understanding of LLM fundamentals — prompting, tool use, reasoning, and evaluation in the context of conversational AI
• Genuine interest in and prior experience with early-stage, high-ownership environments — someone who's excited to build 0-1 and scale 1-10, not just maintain existing systems
• Ability to take technical ownership and lead design/architecture decisions with minimal oversight
• Comfort working in a fast-moving, high-ownership environment, balancing hands-on coding with technical leadership
• Excellent communication skills — this is a customer-facing role, and you'll regularly engage directly with customers to understand needs and explain technical solutions