SQL Experts in Berlin

Evidence-led health intelligence platform turning published research into personal health protocols. It scores 430 habits, foods, and supplements against the studies behind them, and moves the score when the evidence moves. Built solo.

• Built the daily ingestion pipeline across PubMed, bioRxiv, and medRxiv: 43,000+ papers from 3,400+ journals processed into 230,000+ typed evidence claims, each one traceable back to the study it came from.
• Designed the six-factor evidence scoring model and the public changelog behind it, so no recommendation ever appears without the papers underneath it. 23,000+ grade changes recorded and explained to date.
• Shipped an entity information model connecting every intervention to its mechanisms, biomarkers, and outcomes: 118 biomarkers with region-specific reference ranges, 77 mechanisms, 32 graded outcomes.
• Built the personalisation layer: blood panel ingestion that reads lab PDFs with a vision model and corrects results for draw time against the user's wake anchor, plus Oura, WHOOP, and Withings integration for daily readiness context.
• Operate eleven specialised review agents over the corpus and codebase, covering paper curation, retrieval quality, health-claim compliance across EU and US regimes, and security.
• Shipped the Evidence Assistant, a RAG assistant that answers from the claim database and cites the underlying papers, plus a B2B practitioner tier, an Expo React Native app, and localisation across 3 languages and 7 markets.

Stack: Next.js 16, TypeScript, Supabase, pgvector, Anthropic Claude, Vercel, DeepInfra.

• LLM-based features for automated CO₂e data extraction from unstructured documents (70% reduction)

• Agentic AI pipeline for automated Scope 3 emissions calculations with 150.000+ validated data records

• Intelligent API workflows for real-time carbon footprint calculations in ERP and ESG systems

• ML algorithms for predicting emissions hotspots and optimizing product design

• Automated data validation pipelines with NLP for quality assurance of CO₂e datasets

• Led a 15-person cross-functional team in developing 10+ AI features

• Strategic product planning and AI roadmap with 35% shorter time-to-market

• Stakeholder management with DAX companies (40% higher satisfaction, 95% retention)

• On-time project delivery with 95% budget adherence through data-driven backlog management

• Agile methods (Scrum, Kanban) with continuous AI/ML integration (25% increase in team velocity)

• Product-market fit for AI features through A/B testing and analytics (60% higher adoption rate)

• Marketing Strategy: Lead the end-to-end analysis and evaluation of cross-channel marketing campaigns across the entire Customer Journey. My focus is identifying optimization potential and deriving clear, actionable recommendations that drive measurable business impact.
• Data Science & AI: Advanced predictive modeling (Churn, LTV), market basket analysis, clustering, and real-time AI-powered audience discovery utilizing RAG/LLMs.
• Marketing Analytics & Measurement: End-to-end attribution analysis, Marketing Mix Modeling (MMM), audience segmentation, conversion path analysis, and A/B testing across all major platforms.
• Data Engineering & Reporting: Designing and managing robust, multi-platform data pipelines (BigQuery, GCP) for data consolidation, automated dashboard generation, and critical API integrations.

• WiNOWiG enhancements (digitalization & organization)
• Project management for the WiNOWiG project (regulatory offenses)
• Process optimization and coordination

• Shipped Recare Voice Desktop from 0 to 1 in two months, including multi-language clinical documentation that auto-transcribes into structured German medical notes.
• Reduced LLM inference costs by 60–70% across Docs and Extract through prompt caching architecture.
• Built the AI workbench used by PMs/engineers for prompt experimentation and the Langfuse eval stack (10k+ traces evaluated).

Designed and built an end-to-end interactive decision-support application using public European data across 27 EU countries and multiple strategic dimensions. Developed a structured analytical methodology for comparing countries, identifying patterns and trade-offs, and exploring strategic choices rather than presenting static dashboards. Translated complex multidimensional data into guided interactive exploration and learning workflows for non-specialist users. Built the application end-to-end using Python and Streamlit, with AI-assisted development and Git-based version control. Developed the project independently from problem framing and data analysis through methodology, UX logic, implementation and deployment.

Tools: Python, Streamlit, Git, AI-assisted development

[link]

Workflow-automation SaaS for operations teams (Berlin, 120 people); full-time freelance engagement reporting to the CEO: an initial 12-month interim mandate, extended twice through the AI build-out; owned product for one squad and coached the other product managers on process.

• Led generative AI (LLM) integration into the core product: from LLM-powered steps to natural-language workflow authoring and step-level automation suggestions, plus AI-managed dynamic workflows, shipped behind eval gates with human-in-the-loop fallbacks: AI-drafted workflows grew to 31% of all new workflows, and median time-to-first-workflow fell from 3 days to 4 hours.
• Packaged the AI capabilities as a usage-based add-on priced on executed automation steps, working with sales and marketing on positioning: ~€800K added ARR in the first year, and adopting accounts churned 1.8 pp less.
• Owned the roadmap end to end: replaced feature-request-driven quarterly planning with an outcome-based rolling roadmap built on quarterly bets and explicit kill criteria, presented monthly to the executive team and quarterly to the board.
• Rebuilt the product-management operating system: weekly customer-discovery cadence incl. workshop facilitation, RFC/decision-doc reviews and a single quarterly metrics narrative; coached four product managers, one promoted to senior during the engagement.
• Closed the engagement as scoped: hired and onboarded the permanent VP Product, handed over the process playbook and roadmap, and exited on schedule in June 2026.

• PROBLEM: GTM effort is guesswork across fragmented identities and channels, with no closed feedback loop.
• BUILT: Cost-pyramid engine (L0–L3): identity resolution across ~25k entities, explainable intent scoring, and a closed decision loop (propose → execute → evaluate → learn) with calibration.
• IMPACT: Shipped v1.3.1 with a live demo; 99% of operations resolve at the free L0 tier (CI-enforced); $0 to run without any API key.

Driving AI model quality at scale — evaluating prompt-response accuracy, flagging edge cases, and maintaining SLA-compliant workflows across distributed global teams.

• Analyse AI prompts and side-by-side model outputs to assess response quality, factual accuracy, relevance, consistency, and compliance with project evaluation guidelines.
• Perform fact-checking, data validation, troubleshooting, issue identification, and edge-case review to improve quality standards across AI training support workflows.
• Use Google Sheets, Google Docs, and browser-based tools to document findings, maintain evaluation logs, track issue patterns, and support workflow optimisation in a remote environment.
• Create clear written justifications, review summaries, and KPI-oriented reporting focused on accuracy, turnaround time, documentation completeness, defect identification rate, and SLA adherence.

• Used OpenCode and AI-assisted software engineering to design, implement, refactor, test, and document an end-to-end RAW/SDTM/ADaM pipeline in R for Dr. Falk Pharma (07/2026), including metadata-driven transformations, automated validation rules and QC, traceability, and reproducible clinical outputs.

• Architected and deployed private cloud data platform on VMware vSphere, integrating Greenplum MPP, Apache Kafka, Kubernetes, and Apache Solr, and developed real-time ingestion pipelines with Kafka Connect and Schema Registry.
• Led Oracle Exadata to Greenplum migration, rearchitected data models, optimized storage, implemented RabbitMQ with Debezium for CDC, and deployed VectorDB for Generative AI.
• Designed and executed multi-cloud migration PoC across AWS, Azure, and GCP, defined KPIs for throughput, latency, and cost efficiency, executed bulk data transfers, validated analytics and streaming workloads, and delivered full-scale architecture recommendations.
• Assessed legacy on-premises infrastructure and designed modern cloud-native data platforms using Greenplum and containerized microservices, advising on scalability, disaster recovery, and high-availability.

• Own full-stack development of an AI-native enterprise platform built on TypeScript, React, Vite, tRPC, Hono, and PostgreSQL, delivering AI-powered consulting workflows to B2B clients.
• Designed and shipped a multi-agent AI system using ReAct framework and Claude skills-style workflow patterns, including an intelligent PM assistant with rich system prompts, slash commands, tool integrations, and streaming chat UI.
• Architected an LLM evaluation framework: rubric-based LLM-as-judge, golden datasets, regression testing, and automated quality gating — ensuring consistent AI output quality at scale.
• Integrated LangFuse for end-to-end LLM tracing, conversation replays, and evaluation pipelines, enabling data-driven prompt optimisation that reduced token costs and response variance.
• Built with Drizzle ORM, pgvector, and knowledge graphs for structured data access, semantic search, and relationship-aware AI reasoning across the platform.
• Led TanStack React Query migration across the application — replacing manual state management with centralised caching and automatic refetching, reducing data-fetching boilerplate significantly.
• Practiced AI-native development throughout: Claude Code, Codex, Perplexity SDK, and LLM-assisted testing across the full development lifecycle. Deployed on Vercel + Azure ACA with Biome for linting/formatting.

• Designed, built, and launched an internal event planning web application used by over 100 department leads for a large event, despite having no dedicated testing phase.

• Ensured smooth, failure-free operation during first production use, leading to the tool being adopted for future events.

• Automated catering calculations and related workflows, significantly reducing email communication and manual computation effort for meal planning.

• Managed deployment and hosting on a Linux server using Coolify, including application setup and runtime operations.

• Hired and guided a communication designer on UX while independently owning all technical decisions and implementation.

Led FP&A tech transformation for a 9-figure business – from resolving legacy technical debt to leading AI-native EPM implementation

• Driving end-to-end FP&A transformation, from architecture redesign through EPM tool selection to rollout
• Ran evaluation of 12+ EPM platforms, from vendor negotiation to selection framework tied to long-term planning
• Diagnosed constraints in financial planning architecture, presented findings to the CFO, and secured executive mandate to redesign FP&A infrastructure from the ground up