Senior Software Engineer, Voice AI

Your opportunity

Our client is a mission-driven, seed-stage startup modernizing emergency response communications, reducing 911 call wait times and improving public safety outcomes. It’s a Canadian corporation that operates with remote teams distributed across North America. Their core product is an AI-powered voice agent that autonomously handles incoming calls for government services, with an acute focus on public‑safety and city‑service hotlines.

The company is a freshly funded, mission-driven SaaS GovTech led by accomplished, repeat co-founders committed to impacting communities by relieving a critical bottleneck in emergency response communications. The leadership team brings decades of startup experience, multiple exits through both IPO and M&A, and relevant tours of duty in public service and research to the venture. As of May 2025, the company has approximately 10 team members total, and this hire will take the engineering team from 4 to 5 software engineers. The rest of the team serves in sales/go-to-market, operations and leadership roles.

The platform utilizes commercially available and open-source models to provide a sophisticated voice agent capable of triaging 911 calls, automating routine and non-emergent 911 calls, and handling 311 and government service calls. The company differentiates itself from the competitive landscape by focusing exclusively on 911/311 calls and integrating with existing emergency call‑center and dispatch workflows.

R&D is organized into a single cross-functional delivery team led by the co-founder and CTO. Following the close of their seed round, the company is investing in their product velocity and is seeking a senior software engineer to join their budding engineering team.

Key responsibilities 

• Software architecture and engineering: Design and implement event‑driven, real‑time, highly concurrent systems leveraging advanced concurrency patterns (e.g., actor model, goroutines), asynchronous messaging, and performance optimizations to ensure low‑latency, high‑throughput and fault‑tolerance

• Systems architecture and engineering: Collaborate on cloud‑native architecture, infrastructure as code, CI/CD pipelines, autoscaling and load‑balancing strategies, security best practices, and observability efforts

• AI platform engineering: Integrate LLMs and other emerging AI technologies, select and potentially fine‑tune models, orchestrate deployments, and monitor performance

• Audio processing: Design, implement, and optimize audio‑processing pipelines for capabilities such as speech‑to‑text, text‑to‑speech, voice‑activity detection, endpointing, noise filtering, and emotion detection

• Technical leadership and mentoring: Guide architecture and design decisions, conduct code reviews, establish best practices, and coach team members to accelerate their technical growth while reinforcing a culture of continuous improvement

Tech stack

• Back-end: Elixir (Phoenix, Membrane)

• Database: PostgreSQL

• Cloud provider: Azure

• Machine Learning & AI services: OpenAI

• Infrastructure as code / containerization: Terraform, Docker

• Monitoring, alerting & observability: New Relic, incident.io

Your know-how

• You have 4+ years of experience in back-end or full-stack software engineering

• You have an adaptable, resilient disposition suited to a dynamic startup environment

• You have experience designing and implementing event-driven, highly concurrent systems

• You have experience with natural language processing (NLP)

• You have a contagious growth mindset and persistently seek opportunities to improve yourself, the team, products and processes in a scaling business

• You have an excellent command of English

It’s a bonus if

• You have an acute interest in building impact-oriented technology and saving lives with software

• You have helped build or scale an enterprise SaaS venture

• You have designed and operated highly concurrent, fault‑tolerant services using Elixir, Erlang, Go, or an equivalent language

• You have developed and integrated voice‑AI or audio‑processing solutions in production

• You have experience with telephony systems (PSTN, SIP protocols, PBX architectures)

• You have experience with WebRTC technologies (peer-to-peer media streaming, signaling protocols, ICE/STUN/TURN for NAT traversal, data channels, and client-server integration)

• You have experience with Vector databases and similarity search pipelines