Senior Real-Time AI Backend Systems Engineer

GetVocal AI Ltd.; Paris; Hybride; EUR 90 000 - 130 000; Plein temps

Avantages offerts par ce poste

25 days holiday

Private healthcare

Diversified, international team

ESOP/VSOP

Résumé du poste

GetVocal AI Ltd. in France is seeking a Senior AI Software Engineer to design and operate production-grade backend systems powering real-time conversational AI agents.

You’ll build low-latency services with Python, FastAPI, Redis, and event-driven architectures, ensuring reliability under production traffic and integration with LLM providers. The role requires expert Python, asynchronous programming, Docker/Kubernetes, and collaboration with AI researchers to turn experimental capabilities into

Qualifications

• Expert Python skills with production backend experience.
• Strong knowledge of asynchronous programming and concurrency.
• Experience building low-latency, high-throughput real-time systems.
• Familiarity with AI/LLM integration and orchestration.
• Proficient with Docker, Kubernetes, Linux, and cloud platforms.

Responsabilités

• Design, build, and operate production-grade backend systems powering our conversational AI platform.
• Develop low-latency, high-throughput services using Python, FastAPI, and async programming.
• Create real-time event-driven systems using WebSockets, queues, and parallel processing.
• Design distributed architectures robust to production traffic.
• Build AI agent orchestration systems and LLM-powered apps.
• Integrate LLM APIs and external AI providers into the platform.

Connaissances

Python

FastAPI

Asyncio

Distributed systems

WebSockets

Docker

Kubernetes

Redis

AI/LLM integration

Code review & testing

Outils

LangChain

LiveKit

Cloud platforms (GCP/AWS/Azure)

LLM APIs

CI/CD tooling

Description du poste

GetVocal AI Ltd. in France is seeking a Senior AI Software Engineer to design and operate production-grade backend systems powering real-time conversational AI agents.

You’ll build low-latency services with Python, FastAPI, Redis, and event-driven architectures, ensuring reliability under production traffic and integration with LLM providers. The role requires expert Python, asynchronous programming, Docker/Kubernetes, and collaboration with AI researchers to turn experimental capabilities into