> Markdown version of [/jobs/ext/1436745-senior-ai-software-engineer](https://www.wearedevelopers.com/jobs/ext/1436745-senior-ai-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior AI Software Engineer - **Company:** GetVocal AI - **Location:** Paris, France - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Multitier Architecture, Artificial Intelligence, Amazon Web Services, Automation of Tests, Microsoft Azure, Code Generation, Profiling, Continuous Integration, Cursor (Graphical User Interface Elements), Software Debugging, Linux, Distributed Systems, Fault Tolerance, Python (Programming Language), Load Testing, Multiprocessing, Queueing Systems, Redis, Software Tools, Software Engineering, WebSocket, WebRTC, Cloud Platform System, Real Time Systems, Large Language Models, Multi-Agent Systems, Concurrency, Caching, Parallel Computation, Backend, Fastapi, Event Driven Architecture, Build Management, Kubernetes, Low Latency, Production Code, Video Streaming, Virtual Agents, Asynchronous Programming, Api Design, Stream Processing, Code Restructuring, Docker - **Published:** July 25, 2026 - **Apply:** https://fr.indeed.com/viewjob?jk=e3087672bc5a1c80 ## About the Role Expert-level Python skills and strong experience building production backend systems. Advanced knowledge of Python asynchronous programming, including asyncio, concurrency, and multiprocessing. Strong experience with FastAPI and API architecture. Experience building low-latency, high-throughput, or real-time systems in production. Strong understanding of distributed and event-driven system design. Hands-on experience with technologies such as: * WebSockets * Streaming systems * Message queues * Redis and caching * Parallel processing * Event-driven architectures Experience building AI agents, LLM applications, or AI orchestration platforms. Production experience with modern AI technologies such as LangChain or equivalent frameworks, MCP, LLM APIs, and real-time communication platforms such as LiveKit or equivalent. Strong understanding of scalable architecture, system decomposition, modularity, resilience, and fault tolerance. Experience with observability, performance profiling, latency optimisation, load testing, and production debugging. Strong software engineering fundamentals, including clean architecture, maintainability, and automated testing. ## Description We're building the next generation of real-time conversational AI systems., Our agents operate under real production traffic, where latency, scalability, reliability, and engineering quality are critical. We're looking for a Senior AI Software Engineer to design and build the production systems that allow these agents to respond intelligently and reliably in real time. This is not an R&D or research role. This role sits at the intersection of AI engineering, backend systems, and distributed real-time architecture. You will take ownership of complex production systems behind our AI agents, including low-latency backend services, event-driven pipelines, agent orchestration, and the infrastructure patterns required to operate them at scale. We also believe that modern software engineering is changing. The strongest engineers are no longer measured only by how much code they write manually, but by how effectively they can design systems, orchestrate AI coding agents, and validate AI-generated work without compromising quality. What You'll Do * Design, build, and operate production-grade backend systems powering our conversational AI platform. * Build low-latency, high-throughput services using Python, FastAPI, and asynchronous programming. * Develop real-time, event-driven systems using WebSockets, streaming technologies, queues, and parallel processing. * Design distributed architectures that remain reliable and responsive under significant production traffic. * Build and improve AI agent orchestration systems and LLM-powered applications. * Integrate LLM APIs, AI frameworks, communication infrastructure, and external AI providers into the platform. * Use technologies such as Redis and caching layers to improve latency, throughput, and system efficiency. * Profile production systems, identify performance bottlenecks, and optimise critical execution paths. * Improve system resilience, fault tolerance, observability, and production debugging capabilities. * Write comprehensive unit, integration, and load tests. * Design clean, modular, and maintainable architectures that can evolve as the product scales. * Work closely with AI, product, and engineering teams to translate agent capabilities into reliable production systems. * Use AI coding tools to accelerate development, debugging, testing, refactoring, and technical exploration. * Review and validate AI-generated code for architectural flaws, hallucinations, security issues, and maintainability risks. * Write a significant amount of production code while improving the overall engineering quality of the platform., Comfort working with Docker, Linux, CI/CD pipelines, Kubernetes fundamentals, and at least one major cloud platform such as GCP, AWS, or Azure is a strong advantage. AI-Native Software Engineering You should already be using AI coding tools such as Claude Code, Codex, Cursor, Gemini CLI, or equivalent tools as part of your daily engineering workflow. We are looking for engineers who know how to: * Break complex engineering problems into clear, AI-executable tasks. * Write precise technical specifications and prompts. * Orchestrate multiple AI coding agents or workflows in parallel. * Rapidly review, test, and validate AI-generated code. * Identify hallucinations, security vulnerabilities, and architectural weaknesses. * Refactor AI-generated code into clean and maintainable production software. * Use AI to accelerate debugging, testing, documentation, and refactoring-not only initial code generation. * Increase development output without reducing engineering quality or accountability. Using AI tools is not a substitute for strong engineering fundamentals. You must be able to understand, challenge, and take full ownership of everything that enters production. Comfort working closely with AI researchers, product teams, and infrastructure engineers to turn experimental capabilities into reliable production systems. ## Related Videos - [Docker network without Docker](https://www.wearedevelopers.com/videos/1418-docker-network-without-docker) - [Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure](https://www.wearedevelopers.com/videos/1532-agentic-ai-from-theory-to-practice-developing-multi-agent-ai-systems-on-azure) - [Reducing LLM Calls with Vector Search Patterns - Raphael De Lio (Redis)](https://www.wearedevelopers.com/videos/1714-reducing-llm-calls-with-vector-search-patterns-raphael-de-lio-redis) - [Docker Compose: Rediscovered](https://www.wearedevelopers.com/videos/1978-docker-compose-rediscovered) - [Docker exec without Docker](https://www.wearedevelopers.com/videos/1094-docker-exec-without-docker) - [Docker build without Docker](https://www.wearedevelopers.com/videos/100114-docker-build-without-docker) ## Related Articles - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this) - [From Prototype to Production: Build AI Agents with This Free 4-Course Learning Path](https://www.wearedevelopers.com/magazine/655-from-prototype-to-production-build-ai-agents-with-this-free-4-course-learning-path) - [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)