- Build agentic capabilities for TeamViewer Tia and the Agentic Ecosystem, including orchestration, tool use, retrieval, memory, and multi-step task execution
- Define quality criteria, build datasets and evaluation harnesses, and use evaluation results to guide release decisions
- Engineer model context through retrieval strategy, chunking, ranking, caching, compaction, and prompt assembly
- Improve quality through systematic iteration on prompts, tool design, model selection, and orchestration patterns
- Take AI capabilities to production and manage latency, cost, rate limits, fallback behavior, and quality drift
- Partner with product management, security, and platform teams to deliver secure, reliable AI-enabled features
- Apply fine-tuning or smaller specialized models where evaluation evidence supports it
- Work agent-first in engineering and help maintain team context, tooling, and delivery patterns
- Help shape high-quality agentic engineering practices across EMEA teams
Requirements
- 8+ years of industry experience
- Strong Python expertise
- Solid software engineering fundamentals
- Proven track record of delivering production systems
- Hands-on experience building model-based and agentic systems in production environments
- Experience with tool calling, structured outputs, retrieval, orchestration, and multi-agent architectures
- Ability to define AI quality criteria, build evaluation frameworks, interpret results, and identify real-world failure modes
- Data-driven prompt and context engineering experience
- Strong understanding of the current AI model landscape
- Ability to make pragmatic decisions across providers, architectures, cost, latency, reliability, and quality requirements
- Working knowledge of MCP or comparable tool protocols
- Experience with agentic development environments
- Understanding of security implications of giving models access to tools and enterprise systems
- Regular use of AI coding agents with critical review practices
- Accountability for correctness, security, and maintainability of delivered software
- Deep understanding of AI failure modes including hallucinations, context degradation, prompt injection, non-determinism, and silent regressions
- Effective mitigation strategies for common AI failure modes
- Strong communication skills
- Ability to engage with technical and non-technical stakeholders
- Collaborative mindset for working across EMEA teams
Core Competencies
Demonstrates expertise in building and deploying agentic systems, with a strong focus on AI quality criteria, evaluation frameworks, and production-level software engineering. Proficient in Python and experienced in collaborating with cross-functional teams to deliver secure and reliable AI-enabled features.
Highest-signal resume keywords
- Python Expertise
- Production Systems Delivery
- AI Quality Criteria Definition
- Model-Based Systems Engineering
- Multi-Agent Architecture Experience
ATS Optimization Keywords
Hard Skills
- Software Engineering Fundamentals
- Data-Driven Prompt Engineering
- Context Engineering
- Tool Calling
- Orchestration Patterns
- Evaluation Frameworks
- AI Model Landscape Understanding
- Agentic Development Environments
- AI Failure Modes Mitigation
- Critical Review Practices
Soft Skills
- Strong Communication Skills
- Collaborative Mindset
Industry Keywords
- Agentic Ecosystem
- Quality Drift
- Latency Management
- Cost Management
- Security Implications
Tools & Technologies
- MCP Tool Protocols
- AI Coding Agents