• Administration, operation and optimization of Microsoft Intune / Endpoint Manager • Creation, testing and maintenance of software packages (MSI, Win32Apps, PowerShell) • Automation of deployments and configurations (e.g., PowerShell, Graph API) • Analysis and resolution of incidents and 3rd-level support • Support for rollouts, assessments and projects • Documentation, standardization and continuous improvement of workplace services

• Operation, configuration and optimization of Microsoft Teams, SharePoint Online and OneDrive • Consulting and support for business units to ensure optimal use of collaboration tools • Development and maintenance of governance, compliance and security concepts for M365 Collaboration • Support for rollouts, migrations and projects • Monitoring of capacity, performance and availability • Documentation, knowledge building and continuous improvement

Role Description We're looking for an ambitious Mobile engineer (Android) who thrives in the speed of early-stage building. Someone who ships fast, thinks in systems, and isn't afraid to rethink how things are built — including how they build. You'll own critical parts of our mobile product, ranging from hardware integration to smart features, have real influence on architecture, tooling, and the direction of our tech. - Take ownership of the core system that powers Seroton experiences — from concept to scale. - Build, maintain and improve our Android applications and ship features from concept to production. - Improve and evolve our mobile architecture: clean layering, modular systems, scalable patterns. - Own end-to-end delivery across the mobile stack, collaborating closely with hardware integration, product and design to translate complex requirements into elegant mobile experiences. - Use AI-powered coding agents to accelerate your workflow — and champion new ways of working across the team. - Be involved in technical discussions and decisions that shape the product's future and drive them with your opinion. Qualifications - Strong native Android experience with Kotlin. - Experience with Kotlin Multiplatform as well as iOS development is a big plus. - Several years of experience shipping complex products and know what it takes to go from early versions to something solid and scalable. - Systems-level thinker — you see beyond the feature and care about architecture, dependency management, and how things compose. - Comfortable working across boundaries — mobile, backend, APIs, and connected devices. - Actively use AI tools to multiply your output and excited to keep pushing what's possible here. - Product-minded: you care about the experience your code enables, not just the code itself. - Energized by ambiguity, speed, and the opportunity to shape something from the ground up. - Builder mentality with the ambition to grow as the team expands. Benefits - Join a fast-growing start-up and actively shape the experience backbone that future products and features will rely on - your work has a direct impact on our growth. - Take on real projects, contribute your ideas, and receive regular feedback directly from the founders. This position is designed to evolve - more responsibility, more ownership, more impact over time. - Work on a mission-driven product designed to help people reduce stress, improve mental recovery and wellbeing. - A workplace with a diverse, international team offering flexible working models, 30 days of paid vacation, and the opportunity for workations. - Located in the heart of Munich, within walking distance of Olympiapark and well connected to the central station (Hauptbahnhof). - Free drinks, fruit, and coffee, as well as exclusive fitness offers (Wellpass). Company Description Seroton is a fast-growing HealthTech startup redefining mental recovery. We merge the power of meditation and massage into an immersive, full-body experience—making relaxation effortless and effective. App-powered and device-enabled, our smart technology is seamlessly integrated into everyday furniture. The Seroton App acts as the intelligent bridge between hardware and software, delivering personalized experiences and serving as the personal companion for our users.

• Design, build, and maintain production model serving infrastructure using Triton Inference Server as the primary framework • Implement and optimize inference pipelines including custom backends, dynamic batching strategies, and model ensemble configurations in Triton • Optimize Python inference code for performance, with a strong focus on GIL contention, multi-threading, and concurrency patterns • Tune throughput and latency across the full serving stack, batching policies, thread pool sizing, model instance groups, and memory layout • Work closely with the research team to understand new model architectures at a computational level, batching behavior, dynamic shapes, memory access patterns etc • Own the full resource observability and control loop for production inference - instrument GPU memory, CPU, batch queue depth, and latency metrics, and actively tune model instance groups, concurrency limits, memory budgets, and batching configuration in response to observed behavior • Evaluate and integrate alternative inference frameworks and runtimes as the model ecosystem evolves • Contribute to GPU utilization improvements and resource efficiency across the serving fleet