AI Software Engineer (Real-Time Systems)

The Role

We're building the next generation of real-time conversational AI systems.

Our research team is focused on advancing the intelligence layer of our agents. What we’re missing is a strong engineer to own the execution layer — the systems that make this intelligence work reliably, at scale, and in real time.

This role sits at the intersection of AI, backend engineering, and infrastructure.

You will take ownership of the engineering backbone behind our AI agents: performance, latency, reliability, and scalability.

What you’ll do

• Own and evolve the backend systems powering our conversational AI platform.
• Design, build, and optimise real-time systems with a strong focus on latency and performance.
• Maintain and improve our server stack, pipelines, and production infrastructure.
• Develop scalable APIs and services using Python and FastAPI.
• Work closely with the AI research team to integrate new models, ideas, and agent capabilities into production.
• Support and optimise integrations with multiple AI providers.
• Identify bottlenecks, fix bugs, resolve tickets, and continuously improve system reliability.
• Drive improvements in data accuracy, system performance, and real-time responsiveness.
• Write a significant amount of production code and continuously improve existing systems.

What this role is

• This is not a research role.
• You will not be writing papers or training foundation models.
• You will be the person who makes AI actually work in production.

What we're looking for

• Expert-level Python skills and 5+ years of backend engineering experience building production systems.
• Strong experience with FastAPI and asynchronous programming.
• Experience building low‑latency, high‑throughput systems in production environments.
• Hands‑on experience with MLOps tooling (Docker, Kubernetes, GPU workloads).
• Experience working with LLMs, AI agents, or deploying AI systems into production.