Job details

Role Overview
This role is for a mid-to-senior (5+ years) backend-heavy full stack engineer who can deliver production-grade, low-latency voice assistants end-to-end, from telephony and webhooks to real-time AI inference, business workflows, storage, and observability. The frontend is built in Angular, but this position focuses primarily on backend and platform engineering. Your work will sit at the intersection of conversational AI, backend systems, and real-time communication, where milliseconds matter and reliability is critical. Our platform uses Vapi for voice-agent orchestration (transcriber + LLM + voice components) and integrates with Telnyx for programmable voice, SIP, and PSTN connectivity. 

We leverage LLMs such as OpenAI and Gemini models to power agent reasoning and tool use, with a Python-based AI service and a Node.js service as engine coordinating workflows across the system. We are a fast-paced, Agile team that values ownership, practical problem solving, and high-quality execution.

Responsibilities:
•Collaborate with cross-functional teams to define, design, and deliver new features.
•Build, deploy, and iterate production voice agents and supporting services using orchestration patterns (transcriber + model + voice), including prompt design, tool integration, and workflow routing.
•Implement and maintain programmable calling workflows (inbound/outbound), webhooks, call control features, and SIP/PSTN integrations using Telnyx Voice APIs.
•Improve the speed, accuracy, and reliability of the voice assistant by reducing end-to-end latency and improving transcription and dialog quality through streaming techniques, responsive endpointing/VAD, caching, and efficient API/tool design.
•Design and ship RESTful, JSON-based APIs for internal and external use.
•Develop robust, testable backend services across our Python AI layer and Node.js engine.
•Use Redis for caching, rate limiting, and session management, and MySQL for transactional persistence.
•Write clean, maintainable, and efficient code following engineering best practices.
•Participate in code reviews and provide constructive feedback.
•Implement security best practices, data protection measures, and reliable storage solutions.
•Troubleshoot, debug, and resolve production issues in a timely manner.
•Develop automated tests to ensure application quality and stability.
•Collaborate with DevOps to improve deployment, scalability, cost efficiency, and performance on AWS and GCP.
•Contribute to performance analysis and system optimization efforts.
•Create technical documentation and share knowledge with team members.
•Stay updated on relevant technologies, especially in AI and real-time systems.
•Work effectively within an Agile (Scrum) development process.

Requirements:
•Bachelor’s or master’s degree in computer science, Software Engineering, AI, or a related field (or equivalent experience).
•At least 5 years of professional software engineering experience, with meaningful ownership of production services in fast-paced environments.
•Strong backend engineering ability in Python and Node.js, including building scalable services and API-first architectures.
•Hands-on experience building, deploying, or operating voice assistants or real-time conversational systems, including familiarity with telephony concepts (VoIP/SIP/PSTN).
•Practical experience integrating LLM-based features using platforms such as OpenAI and Gemini.
•Understanding of performance considerations in interactive systems, including latency and reliability.
•Experience with real-time streaming architectures (audio streaming, partial results, interruption handling).
•Strong knowledge of relational databases (e.g., MySQL) and caching systems (e.g., Redis).
•Experience deploying and operating services on AWS and/or GCP.
•Familiarity with payment gateway integrations and associated security considerations is a plus.
•Experience integrating third-party APIs and external services.
•Knowledge of containerization technologies such as Docker (Kubernetes is a plus).
•Experience with monitoring and logging tools (e.g., CloudWatch, ELK, Cloud Logging).
•Understanding of authentication and authorization across distributed systems.
•Familiarity with CI/CD pipelines and automated testing practices.
•Experience collaborating with frontend teams (Angular-based applications).
•Practical experience integrating the Google APIs ecosystem.
•Strong understanding of using modern AI-assisted development tools (e.g., Cursor, Copilot) to accelerate delivery while maintaining engineering rigor
•Strong problem-solving skills, communication abilities, and a collaborative mindset.

How we work and how success is measured
We operate in a fast-paced, Agile environment where engineers are expected to take ownership, deliver iteratively, and continuously improve system quality.
Success in this role is measured by:
•Improvements in latency and responsiveness of voice interactions.
•Increased accuracy, reliability, and task completion rates of the assistant.
•Stable, scalable production systems with minimal incidents.
•High-quality code delivery while maintaining speed and engineering discipline.

Salary: Competitive salary and perks

Location: Remote