Staff Software Engineer, AI Voice Agent
Aircall is a unicorn, AI-powered customer communications platform used by 22,000+ companies worldwide to drive revenue, resolve issues faster, and scale customer-facing teams. We’re redefining customer communications by bringing voice, SMS, WhatsApp, and AI together into one seamless workspace.
Our momentum comes from a simple idea: help teams work smarter, not harder. Aircall’s AI Voice Agent automates routine calls, AI Assist streamlines post-call work, and AI Assist Pro delivers real-time guidance so people can do their best work. The result is higher revenue, faster resolutions, and teams that scale with confidence.
Aircall is headquartered in Paris, our European HQ, with a strong North American presence anchored in Seattle, our North American HQ, and teams across Madrid, London, Berlin, San Francisco, New York City, Sydney, and Mexico City. We’ve built a product customers love and a business that’s scaling quickly, backed by world-class investors and driven by rapid AI innovation across multiple product lines.
At Aircall, you’ll join a company in motion. We’re ambitious, product-driven, and execution-focused, with visible impact, fast decisions, and real growth.
How we work at Aircall: We’re customer-obsessed, data-driven, and focused on delivering meaningful outcomes. We value ownership, continuous learning, and thoughtful speed. If you thrive in a collaborative, fast-moving environment where trust and impact matter, you’ll feel at home here.
About Your Role:
At any given moment, businesses running on Aircall are fielding calls their teams can't handle alone. Outside business hours, during peak volume, across languages, around the clock. Our AI Voice Agent is what answers. It's not a simple IVR or a canned response bot. It's a real time AI voice agent that understands context, talks to customers naturally, executes actions mid-conversation, and knows when to hand off to a human.
As a Software Engineer on this team, you'd work at the intersection of real time systems, production LLM applications, and voice infrastructure. The problems are hard in a specific way: milliseconds matter when someone's on the line, latency shapes whether a conversation feels natural or robotic, and the quality of your work is immediately audible to thousands of customers.
This isn't AI prototyping. It's production AI at scale, and one of the fastest moving product areas at Aircall.
- Real-time Speech Pipeline: You'll work on live audio systems: buffering, streaming, latency optimization, and the integration points with speech providers. When latency creeps up, you investigate and fix it. When a new provider looks promising, you evaluate and potentially integrate it.
- The Conversation Intelligence: Conversation quality depends on how well we manage the LLM layer. Prompt construction, context management, function calling, instruction ordering. You'll build and improve the systems that make conversations feel natural: dynamic knowledge injection, action execution with branching logic, and the dialogue management that turns a phone call into something useful.
- Actions and Integrations: Businesses configure AI Voice Agent to execute tasks during calls. Look up account data, create tickets, check order status. You'll work on the action framework: configurable API calls, success/failure branching, auth management and the runtime execution engine.
- Knowledge and Memory: A voice agent is only as good as what it knows. You'll work on how agents ingest, store, and retrieve knowledge at runtime. There's also the question of memory: how agents retain information across a conversation, learn from prior interactions, and use context to give better answers over time.
- Agent Lifecycle and Configuration: Customers need to create, configure, test, and deploy voice agents easily and intuitively. You'll work with our designers to translate cutting edge advanced AI concepts and features into smooth, reliable and easy to use product experiences.
- Evaluations and Quality: Voice AI quality is measurable. You'll help build evaluation frameworks for each model involved, post-call analytics, call quality metrics, and Datadog instrumentation. You'll also be part of the on-call rotation.
- You have experience building production backend systems ideally in Python or Typescript (all levels welcome, 5+ years for senior roles).
- You write async code naturally, understand how to design for performance and reliability, and have shipped systems that real users depend on.
- You understand what makes real-time systems different from request/response API’s. You can talk about the tradeoffs around buffering, streaming, connection management, and latency.
- You've worked with LLMs or AI/ML systems in production. You understand concepts like prompt engineering, context management, function calling, and what it takes to make AI behavior reliable for customers.
- You know evaluation matters and you've built or used tooling around it.
- Event driven architectures, message queues, caching layers, and async task processing feel natural to you.
- You've debugged distributed failures and designed systems that handle partial failures gracefully.
- Testing strategy, observability, API design, and code review are things you do thoughtfully. You write code that other engineers can understand and extend.
- You communicate clearly. You can explain a complex technical problem to someone without your context, write a design doc that prevents misalignment, and ask good questions before diving into implementation.
- You are familiar with AI coding tools and already embedded them into your day to day engineering processes.
- Experience with voice, audio, or telephony systems
- Prior work with STT or TTS providers and models
- Familiarity with LLM evaluation frameworks and quality metrics for AI outputs
- AWS experience, particularly DynamoDB, Lambda, AppSync, or SQS
- GraphQL API design experience
- Kubernetes and infrastructure as code (Terraform, Helm)
Why join us?
🚀 Key moment to join Aircall in terms of growth and opportunities
💆♀️ Our people matter, work-life balance is important at Aircall
📚 Fast-learning environment, entrepreneurial and strong team spirit
🌍 45+ Nationalities: cosmopolite & multi-cultural mindset
💵 Competitive salary package & equity
🏨 Medical, dental, and vision insurance is 100% covered
📈 401k plan with company matching!
✈️ Unlimited PTO — take the time you need to come to work feeling great!
⭐️ Wellness, commuter, and childcare reimbursements
💚 Generous parental leave policy
DE&I Statement:
At Aircall, we believe diversity, equity and inclusion – irrespective of origins, identity, background and orientations – are core to our journey.
We pride ourselves on promoting active inclusion within our business to foster a strong sense of belonging for all. We’re working to create a place filled with diverse people who can enrich and learn from one another. We’re committed to ensuring that everyone not only has a seat at the table but is valued and respected at it by providing equal opportunities to develop and thrive.
We will constantly challenge ourselves to make sure that we live up to our ambitions around diversity, equity and inclusion, and keep this conversation open. Above all else, we understand and acknowledge that we have work to do and much to learn.
Want to know more about candidate privacy? Find our Candidate Privacy Notice here.
Average salary estimate
If an employer mentions a salary or salary range on their job, we display it as an "Employer Estimate". If a job has no salary data, Rise displays an estimate if available.
Wellmark is hiring a Software Engineer to design and build data-focused integrations and pipelines that support HEDIS and quality measurement in a regulated healthcare environment.
Lead and mentor a software engineering team at Renesas to deliver high-quality embedded and application software while driving execution and cross-functional collaboration.
Experienced network automation engineer needed to build and maintain Python automation, NetBox integrations, and multi-vendor networking workflows for a client-facing engineering team.
Experienced backend-focused full-stack engineer to build and maintain scalable Ruby on Rails services integrated with React and GraphQL for a healthcare data intelligence platform.
Constellation Technologies is hiring a TS/SCI-cleared AI Software Engineer to lead LLM orchestration, data engineering, and secure deployment efforts for mission-critical systems.
Senior Architect role to design and implement high-performance AI communication and memory libraries while driving hardware-software co-optimization across GPUs, DPUs, NICs, and interconnects at NVIDIA.
Staff Software Engineer to build and scale AI-native full-stack products at HubSpot Foundry, shipping rapid prototypes and production-ready features that help SMBs grow.
Help scale Chime's AI-powered Jade assistant by building platform tooling, backend services, and observability systems as a Senior Full-Stack Engineer.
Senior Salesforce Developer role at a data analytics and Salesforce consultancy, driving architecture, AI-assisted development, and cross-functional solution delivery in a fully remote environment.
Help build TierZero's core product as a founding engineer, designing agentic LLM systems, ML pipelines, and scalable infrastructure to accelerate how teams run code in production.
Contribute to Isaac Lab as a Software Engineering Intern focused on building scalable simulation, perception-in-the-loop RL, and sim-to-real capabilities for robot learning at NVIDIA.
Join Patreon's Identity & Access team to design and implement authentication, verification, and account-protection features that keep creators and their supporters safe and secure.
Senior Technical Architect needed to lead architecture, prototyping, and technical decisions for R&D product work on a Tiered Pricing Mechanism in a remote Web3/DeFi research unit.
Through a combination of its powerful software and dedicated people, Aircall helps SMBs drive productivity and turn customer and employee satisfaction into key growth drivers.
4 jobs
🔮
Hi, I'm Risa! Your AI Career Copilot
you, just ask me below!
