AI Software Architect

AI Software Architect

TeamViewer

Linz, Austria

Responsibilities

The Agentic Ecosystem team is building the foundation for AI-native enterprise software. We create platform capabilities that allow AI agents to understand context, discover tools, invoke capabilities, and execute governed actions across TeamViewer products and connected third-party systems.

The work sits at the core of agentic experiences: MCP servers and clients, tool catalogs, context assembly, orchestration, evaluation, observability, secure integration patterns, and production-grade guardrails. The goal is to make agent behavior reliable, measurable, auditable, cost-aware, and safe for enterprise use.

You will help define how autonomous agents become trusted components of real-world software, not experiments or demos. This means combining strong engineering standards, AI-native development practices, human accountability, and customer trust. Join us if you want to build the ecosystem that will power the next generation of intelligent digital work.

• Own the architecture of TeamViewer’s agentic platform, including Tia, third-party agents, tool use, retrieval, memory, orchestration, and governed actions across TeamViewer ONE.
• Define reference architecture for MCP servers and clients, tool catalogues, context assembly, memory, orchestration, and trust boundaries.
• Establish evaluation and observability discipline by defining quality criteria, tracing agent behavior, catching regressions before release, and using results to guide architectural decisions.
• Set pragmatic positions on model choice, routing, fallback behavior, cost governance, vendor dependency, and production reliability.
• Design safety architecture with security partners, covering prompt injection containment, permission models, tenancy isolation, auditability, and AI component risk.
• Guide teams hands-on through early project phases, conduct architecture and design reviews, mentor senior engineers, and maintain clear architecture documentation for both engineers and agents.

Requirements

• 10+ years of software engineering experience, including demonstrated expertise in complex architectures, strong Python and TypeScript skills, and deep knowledge of distributed systems.
• Extensive experience designing and delivering agentic systems, including tool-using agents, MCP or comparable protocols, retrieval, context engineering, multi-agent orchestration, and evaluation frameworks.
• Proven track record of bringing AI solutions into enterprise production environments, with a strong understanding of security, compliance, multi-tenancy, cost management, reliability, and operational excellence at scale.
• Strong ability to evaluate AI systems responsibly by defining quality standards, developing evaluation approaches, interpreting results, and identifying real-world failure modes.
• Deep understanding of common AI model failure modes, including hallucinations, context degradation, prompt injection, non-determinism, and silent regressions, as well as the architectural controls required to mitigate them.
• Regular use of AI coding agents, combined with critical review practices and accountability for correctness, security, maintainability, and architectural alignment.
• Ability to communicate complex architectural concepts effectively to both technical and non-technical stakeholders, balancing business value with technical considerations while collaborating across global teams.
• Solid knowledge of software licensing, open-source compliance, and AI dependency risk, complemented by a Bachelor's or Master's degree in Computer Science, Software Engineering, or a related field.