Mistral AI Experts in Berlin

• Conducting cybersecurity readiness checks based on an in-house assessment methodology
• Analyzing the external attack surface using the Graydaxe EASM platform
• Assessing maturity levels and deriving prioritized recommendations for action

• Built a JTBD-based prioritization framework for 3,000+ accumulated feature requests, identified 27 broker jobs, validated 8 through 25 user interviews, and used the resulting job map as a live prioritization filter for all incoming channels (Upvoty, CSAT, consulting tickets).
• Responsible for the Scout24 Lighthouse initiative: Document Intelligence with full RAG architecture (semantic chunking, bge-m3 embeddings, pgvector, BM25+Dense hybrid retrieval).
• Reduced lead time of customer feature requests to 3.1 days through code analysis, ticket specification, and independent implementation using a coding agent (Codex).
• Developed an LLM-based support agent (GPT-4o mini, Codex-generated merge requests) that reduced 3rd-level escalations from 40% to 5% of all monthly tickets.
• Integrated six partners through technical coordination, specification, backlog and release management, and led seven full stack developers.
• Eliminated regulatory exposure for brokers in six weeks through risk analysis (BGH ruling on distance selling/GDPR), new audit features, and coordination with legal and data protection officers.

• Developed and implemented organization-wide discovery framework based on Ulwick’s Outcome-Driven Innovation; enabled 7 Product Owners to systematically identify and quantify unrealized value through shared outcome language and opportunity scoring methodology
• Transformed Product Owner role from backlog clerks to strategic experimenters; established dedicated time budget for autonomous hypothesis testing and discovery activities
• Rebuilt customer journey maps to start at actual user need (tool selection phase) instead of platform entry point; eliminated manual data aggregation work previously done by project teams
• Implemented OKR framework across 4 product teams; defined quarterly objectives with measurable key results (e.g., 40% reduction in manual integration effort, self-service adoption increase)
• Unified 3 separate platform roadmaps through cross-team dependency mapping and shared service agreements
• Supported enterprise sales cycle with ROI modeling and technical due diligence for automotive and defense customers

• Delivered a new notifications platform implementation built from scratch to replace existing and upcoming services
• Collaborating with other teams to integrate more domains

Tech stack:

• Data: Scala 3, Apache Kafka, Python, Airflow, Astronomer
• BE-FE: TypeScript, NestJS, Java, Spring Boot, Vue
• Dev-ops: AWS, PostgreSQL, Docker, GitHub Actions, Kubernetes, Helm, ArgoCD

• Pioneered first enterprise AI-SAP integration at ALDI SÜD, deploying AI-driven automation within one of retail's largest SAP S/4HANA programs, eliminating 50% of manual pre-cycle validation time and establishing replicable automation framework across 11 countries
• Led end-to-end SAP project lifecycle management for implementations across SAP S/4HANA and Manhattan Systems, supporting 7,300+ ALDI SÜD locations globally across Europe and Australia
• Served as primary executive liaison to C-level stakeholders across 11 countries for strategic SAP transformation programs
• Orchestrated automation, performance, and volume testing for critical releases, maintaining 99.9% system SLA compliance during peak retail periods
• Managed cross-functional international teams of 15+ specialists, delivering projects 20% faster than industry benchmarks
• Standardized SAP processes across 11 countries as part of one of retail's largest SAP implementations
• Directly managed €2M budget with 98% allocation accuracy across 12 concurrent projects
• Reduced SAP S/4HANA migration costs by 18% through strategic vendor contract renegotiations and optimization

• Elevated LLM output reliability by engineering domain-specific prompts and evaluation logic, improving reasoning consistency across production language model workflows.
• Designed advanced coding benchmarks and validated solutions to strengthen training and evaluation datasets, improving model performance on technical problem-solving tasks.
• Designed and implemented automated evaluation frameworks for technical reasoning tasks; optimized LLM output reliability by 15% through rigorous prompt engineering and rubric-based benchmarking.

• Developed a custom tool using the Mistral 7B LLM to scan, validate and report security vulnerabilities.
• Security tested AI agents, bots, and other LLMs with a focus on prompt injection, model inversion, data poisoning, EDR/AV bypass and evasion techniques, membership inference, model evasion, overfitting to malicious inputs and contextual manipulation.
• Onboarded repositories to SAST solutions for security scanning, implemented secrets scanning, DAST, SCA, and utilized ZAP for DAST in CI/CD pipelines.
• Engaged in security awareness trainings, developed CTF challenges and training materials to enhance developer security knowledge.
• Planned and executed bi-annual red teaming operations based on the MITRE ATT&CK framework and led internal and external pentests based on the OWASP Top 10 framework for 70+ applications worldwide, resulting in detection, reporting, and remediation of hundreds of vulnerabilities.
• Triaged HackerOne reports.

• Developed Red Team infrastructure for real-world attack simulations using Sliver C2 and custom tools
• Executed advanced Red Team operations, integrating AI/LLM security research for prompt injection attacks
• Conducted comprehensive breach assessment attacks and vulnerability assessments across enterprise infrastructure
• Performed root cause analysis and purple team exercises, generating executive-level reports
• Lead LLM red teaming initiatives to improve AI model security for GPT-4, Mistral, and internal GenAI models

• Introduced a serverless/event-driven platform, boosting deployment frequency from 3 to 40 per month
• Implemented an LLM-based fraud-detection proof of concept that flagged 92 % of suspicious transactions
• Built performance and DORA metrics dashboards adopted by the C-suite

• Implemented RAG architecture with Mistral AI APIs to help people find relevant events, job links and other details related to their job search and career.
• Used Tailwind UI components and Flowbite.

• Designed and implemented end-to-end automated workflows for extracting structured data from semi-structured PDF documents including invoices and medical reports
• Leveraged Optical Character Recognition (OCR) technology and large language models to parse documents and generate validated JSON schemas
• Engineered prompt optimization strategies and rule-based classification hierarchies to enhance parsing accuracy across diverse document layouts
• Established quality assurance framework using evaluation metrics to validate output against ground truth datasets with 96% accuracy