Observability Experts in Frankfurt

• Fully on-premises LLM document-examination platform for a compliance-critical banking domain: agentic LangGraph pipeline with deterministic verification, every AI judgment structured and source-anchored; ~960 automated tests, zero data egress
• GPU throughput engineering (quantized serving, speculative decoding, prefix caching): 9.5x extraction speed-up, 500+ multi-document case files per day on a single A100
• AI-native EDI/EDIFACT integration platform (~116k LOC Java 25 / Spring Boot 4, 1,900+ tests): LLM-drafted partner mappings machine-verified before go-live (DFDL conformance, field-coverage checks, dry runs), ~99.5% byte match on real customer files — replacing weeks of manual mapping per partner

• Built an MCP (Model Context Protocol) layer for Mwanachama's agency service, turning domain manager methods into callable AI-agent tools. This included a composite tool that builds a full organization design (org chart, goals, workflows, RACI matrix) from one specification.
• Built the chat-driven agency builder (Wakala Studio and API), where an organization describes its structure in natural language and an AI agent uses those tools to construct and modify the live design.
• Added an insights service so an organization can review AI-agent interactions and completed work. Insights from that review feed back into solution design, gated by architect and user sign-off.
• Alongside this, designed and built the platform itself: ~20 Go microservices on PostgreSQL, Flutter and React clients, deployed on Kubernetes.
• AI agents scan the platform autonomously for security gaps and run scripted tests, covering API (Postman-style) and UI testing. The rest of the work stays supervised. No rogue agents, promise.
• Building an AI-native enterprise platform that structures organizational data, workflows and responsibilities for both people and AI agents.
• Models accountability through RACI, allowing human and AI participants to take different operational roles, including Responsible, Accountable, Consulted and Informed. AI agents can also take controlled approval roles where the organization assigns that responsibility.
• Extended the organizational and operational-risk themes from my Executive MBA thesis into software, making roles, processes and controls explicit and machine-readable.
• Structures enterprise context so LLM interactions use more relevant information instead of repeatedly processing large amounts of unstructured content.

• Error analysis and fixes including performance optimization of the in-house developed platform API
• Change and incident management in day-to-day operations
• Responsible for compliance with security and compliance requirements
• Vendor management for software development and maintenance
• Planning and execution of migration of legacy services to a cloud native platform

Role in the project: project staff, implementation team

Used skills: requirements analysis, IT service and application management, IT operations, error analysis and performance optimization, software maintenance and lifecycle management

Project environment: Cloud Native Platform (Kubernetes, Crossplane, AWS, ArgoCD, Grafana)

• Led design, development, and deployment of data solutions supporting a major pharma acquisition for Takeda Pharmaceutical Company, delivering transparency reporting systems across Azure,Databricks (Python and Shell Scripting) platforms.
• Owned,Designed and developed scalable ELT pipelines to process Customer and Product data using Azure, complex SQL, Databricks, and shell scripting, enabling efficient data integration and processing across multiple sources including job orchestration and workflow automation.
• Implemented performance optimization techniques (query tuning, parallelism, workload optimization), improving system efficiency and processing time.
• Applied strong analytical and problem-solving skills to assess technical solutions and support business requirements for compliance and transparency reporting.
• Designed scalable data foundations suitable for downstream analytics and AI workloads.
• Led data quality initiatives by assessing multiple source data, defining quality metrics, and establishing processes for monitoring and continuous improvement.

• Database design with Oracle DB, JPA and Flyway considering high performance requirements
• Analysis of multiple architecture drafts and identification of technical risks
• Design and implementation of various interfaces and integrations, especially REST APIs and Kafka topics
• Setup of Elasticsearch for monitoring and analyzing log data
• Establishment of an iterative work approach in the project team facing complex business requirements

• Tech Stack: Java 17, Spring Boot, Microservices, REST, GraphQL, Spring AI, Jenkins, Docker, Git/Bitbucket, JUnit, Splunk
• Led a team of 6 to deliver policy, claims, and onboarding modules serving 50k+ users, maintaining 99.9% uptime
• Cut release cycle time by 35–40% by automating CI/CD with Jenkins and Docker
• Implemented trunk-based branching in Git/Bitbucket
• Integrated 10+ REST APIs and streamlined customer workflows, boosting process automation by 40%
• Increased system stability with proactive Splunk alerting and runbooks, reducing outages by ~25%
• Driven quality with JUnit tests (92% coverage) and code reviews; enforced standards with static checks such as SonarQube

• Further development and creation of data flows for health insurance providers
• Data management across various storage systems (DB2, MSSQL, PostgreSQL, S3, custom APIs, ...)
• Documentation and training
• Planning and deployment of NiFi 2.x (major upgrade)
• Integrating Grafana for visualization, monitoring, and alerting
• Extensive use of the NiFi API to continuously monitor the system and its components