You want to help build a secure, scalable platform that powers real-world software products? Then join our development team and help shape the technical foundation for the next generation of our software solutions.
At Validas, you will take responsibility for the development and continuous improvement of our AI infrastructure. In this role, you will create the foundation for the secure, reliable, and efficient use of modern AI technologies across our products and internal processes.
You will play a key role in expanding our AI capabilities and driving innovation throughout the organization. Your responsibilities will include, among others:
- Software Development and Integration: You will develop and enhance innovative software solutions for our Validas products, internal tools, and business processes. In this role, you will integrate modern AI capabilities into existing applications using secure APIs, services, and workflows.
- AI and LLM Platform: You will design, operate, and continuously improve our internal AI and LLM infrastructure. In addition, you will deploy and manage self-hosted Large Language Models as inference services and evaluate suitable models, model formats, and quantization techniques.
- Performance and Operations: You will optimize context handling, KV cache and memory consumption, throughput, latency, and hardware resource utilization. You will also ensure reliable operations through monitoring, backup and recovery processes, and proactive capacity planning.
- Linux, GPU, and Infrastructure: You will administer the underlying Linux systems and manage GPU and accelerator hardware, including drivers, primarily the CUDA toolkit and driver stack. Furthermore, you will support multi-GPU configurations and hardware upgrades.
- Security and Governance: You will protect our AI infrastructure against prompt injection, data leakage, and misuse by implementing guardrails and content filters, and you will secure the platform through RBAC, SSO, audit logging, and secrets management.
- Documentation, Architecture and Quality: You will create technical specifications, operational documentation, and security designs, while contributing to architectural decisions. In addition, you will ensure the quality, stability, and maintainability of our systems through testing, code reviews, monitoring, and structured root cause analysis.
Ihre E-Mail-Jobbenachrichtigung ist jetzt aktiv!
