We're looking for a skilled Software Engineer to help design and scale advanced AI-driven voice agent platforms used in complex, real-time healthcare conversations. You'll work on building low-latency speech/LLM pipelines, orchestration layers, and reliability systems that drive high-stakes, user-facing AI products.

🎯 Responsibilities

1. Design, build, and deploy end-to-end software products, from architecture through production readiness
2. Develop and maintain low-latency speech and large language model (LLM) pipelines
3. Engineer orchestration layers and systems focused on scalability, reliability, and performance
4. Collaborate on solutions for AI agents that require real-time reasoning and adaptivity
5. Support large-scale distributed deployments, ensuring effective handling of thousands of daily calls

🛠️ Requirements

1. 3-5 years of experience delivering software products end-to-end, including architecture, implementation, and deployment
2. Strong understanding of relevant technologies: FastAPI (Python) backend and React (TypeScript) frontend, or similar stacks in other languages
3. Hands-on experience working with LLMs, AI agents, or other machine learning models, including creating user-facing products
4. Ready to address the challenges involved in deploying AI voice agents at scale
5. Bachelor’s or Master’s degree in Computer Science, Engineering, Mathematics, Physics, or a related field, or equivalent practical experience
6. Demonstrates a founder mindset: strong ownership and a drive for learning and impact

➕ Nice to have

1. Familiarity with large-scale distributed systems and asynchronous workload orchestration
2. Direct experience with platforms such as Pipecat for voice agents

1. Initial conversation to understand who you are, what you want to do, and where you wanna go (30 minutes)
2. Work on a take-home challenge to discuss in the following interview
3. Review your solution with a couple of engineers from the team (60 minutes)
4. Talk with the co-founder (60 minutes)
5. Offer stage