Company Description

At T-Systems, you will find groundbreaking projects that contribute to social and ecological well-being. We want to welcome new talents like you, who bring fresh ideas, different perspectives, embrace challenges, and are committed to continuous learning in order to grow and make an impact on society... all in a fun way!

It doesn't matter when or where you work. It's about doing meaningful work that advances society. For this reason, we will do everything possible to ensure that you have all the development opportunities by providing a support network, excellent technology, a new work environment, and the freedom to work autonomously. We support you in growing both personally and professionally so that you can make a notable impact on society.

T-Systems is a team of around 28,000 employees worldwide, making us one of the leading global providers of end-to-end integrated solutions. We develop hybrid cloud solutions, artificial intelligence, and drive the digital transformation of companies, industries, the public sector, and ultimately, society as a whole

Job Description

T-Systems is at the forefront of innovation, delivering advanced technology solutions across sectors including automotive, healthcare, and public services. Our AI Foundation Services team builds the platform infrastructure that powers AI inference at scale, including API gateways, authentication, billing, and multi-tenant serving.designs and builds high-performance backend systems and APIs that power intelligent applications across diverse industries. We cultivate a collaborative engineering culture where technical depthcreativity and ownership technical expertise drive real-world impact.

Role Overview
We are looking for a senior backend engineer highly skilled Python Developer with strong system design skills and experience building production infrastructuredeep experience designing, building, and scaling distributed systems and APIs. In this role, YyYou willou will own architect and drive the evolution of the maintain backend platform behind our AI inference endpoints - a multi-tenant system handling authentication, API key management, usage metering, billing and request proxyservices that enable high-availability, data-intensive AI-powered solutions. The role is high-ownership and you will shape architecture decisions, raise the bar of engineering quality and build systems that are performant, secure and observable at scale. You'll collaborate with experts in AI infrastructure and data engineering to build robust, secure, and efficient systems that scale to millions of requests.
Responsibilities

• Design and build core platform services: API gateway, authentication, authorization, key rotation, and multi-tenant isolation.Design, implement, and optimize APIs and backend systems using Python frameworks such as primarily FastAPI (or Flask, or Django).
• Architect and implement usage metering, billing integration, and rate limiting for inference endpoints.Build and maintain scalable, fault-tolerant microservices for data processing and AI integration.
• Build and operate a high-throughput proxy/routing layer for AI model serving traffic.Collaborate with cross-functional teams to design system architecture and ensure seamless system interoperability.
• Design telemetry and observability into the platform from the ground up - structured logging, distributed tracing, metrics, and alerting.Implement robust CI/CD pipelines, monitoring, and observability for high-performance production systems.
• Drive technical decisions on architecture, data modeling, and technology choices.Identify performance bottlenecks and drive improvements in reliability, scalability, and latency.
• Establish engineering standards for the backend codebase: testing, code review, CI/CD, and deployment practices.Ensure best practices for security, compliance, and maintainability across the API lifecycle.
• Collaborate closely with the ML infrastructure team to integrate with model serving systems (e.g., NVIDIA Dynamo, vLLM, SGlang, TensorRT-LLM).

Videos To Watch