GitHub Experts in Essen

Tools: Fabric, AWS, dbt, Power BI, SQL, DWH, R, Python

• Supported customers in implementing an architecture design for extracting and preparing data
• Planned the design and implementation of the BI and DWH platform
• Ensured the scalability and performance of the data platform

• Title: Enhancing Syntactic Awareness in Transformer Language Models for Hindi Dependency Parsing
• Investigated syntactic knowledge captured by transformer language models (RoBERTa, XLM-RoBERTa) for Hindi dependency parsing, a morphologically rich and low-resource language.
• Developed structure-aware model variants (Struct_Roberta_hi, Struct_XLMR) by integrating a CNN-based parser network between transformer layers, inspired by the StructFormer architecture.
• Conducted extensive error analysis including label-wise, distance-based, direction-based, sentence length-based, and LVC/Non-LVC evaluations.
• Evaluated models on downstream NLP tasks (NER, POS tagging) using the IndicXTREME benchmark.

(Maternity/Parental Leave: July 2023 – Aug 2024)

• Domain: Payment Domain | Client: Telefonica Germany
• Project: General Payment Service

The General Payment Service is responsible for processing of online payments via external payment service provider like Safer pay and PayPal

• Developed Design of Use (DOU) and interface contract documentation, ensuring clarity and compliance across system integrations
• Designed and delivered REST/SOAP web services with Spring Boot and Spring Data JPA, publishing Swagger contracts through WSO2 API Gateway to improve accessibility and governance.
• Spearheaded the on-premises to AWS Cloud migration, re-platforming from Oracle to PostgreSQL on AWS RDS and deploying services on EC2, improving scalability and cost efficiency.
• Containerized microservices using Docker and orchestrated deployments with Kubernetes, streamlining deployment pipelines and improving system reliability.
• Implemented proactive monitoring and logging via AWS CloudWatch and Kibana, ensuring stability and performance during cutover.
• Enhanced collaboration through code reviews and peer reviews, promoting maintainability and clean coding standards.
• Strengthened quality by writing comprehensive JUnit tests and preparing detailed test cases enabling early defect detection
• Delivered automated API testing with Ready API, Postman, and SOAPUI, and conducted performance testing with JMeter, ensuring reliability in high-transaction environments.

Conventional Paradigm Test (CPT) – AI Evaluation & LLM Research

Development of an experimental evaluation approach to examine “paradigmatic closure” in Large Language Models — that is, the question of how far LLMs can recognize the basic assumptions, values, and limits of the paradigms within which they generate answers.

Design and testing of an additional approach to classic AI benchmarks that does not primarily measure factual correctness or task performance, but instead examines a model’s ability to recognize alternative perspectives, make implicit assumptions visible, and reflect on the limits of its own answer or interpretation framework.

Focus areas: development of evaluation criteria and test questions · LLM evaluation and comparative model analysis · prompt and response analysis · qualitative classification of model answers · study of epistemic compression and value leakage · benchmark and literature research · development of structured assessment and analysis methods

As part of CPT, existing AI evaluation approaches and benchmarks were analyzed, and a minimalist test protocol was developed that classifies model answers by response patterns such as DIRECT, CLARIFY, PLURALIST, REFUSE, and META-AWARE. TruthfulQA was used as the basis for experimental application and comparison with existing reference answers.

Technologies & Methods: Large Language Models (LLMs) · Generative AI · Prompt Engineering · AI Evaluation · TruthfulQA · Benchmark Analysis · Human-in-the-Loop Evaluation · Qualitative Content Analysis · Research & Literature Review

• Gathering, analyzing, specifying, and prioritizing requirements for the 'Archive and Delete' module of the Chambers of Industry and Commerce in a Scrum team
• Capturing and specifying screen/form designs, functionality, and data types in Confluence, as well as creating user stories in Jira
• Preparing PowerPoint presentations for the 'Archive and Delete' module
• Coordinating and supporting the Chambers of Industry and Commerce in the implementation of the module
• Writing SQL scripts for an Oracle database
• Technologies used: Scrum, Confluence, Jira, MS Office, Postman, JavaScript, REST API, JSON, DBVisualizer, SQL

• Strategic transition into AI Engineering through intensive mentoring and project execution.

• Developed MASX AI, an agentic AI platform integrating LangGraph, AutoGen, and RAG for geopolitical forecasting and real-time ETL.

• Designed and delivered functional AI prototypes for prospective clients showcasing applied expertise in multi-agent systems, real-time data pipelines, and LLM integrations.

• Primary point of contact for stakeholders (particularly Group Controlling), responsible for the end-to-end Plan-to-Steer process as well as data-driven corporate planning and performance management using SAP Signavio, SAP Analytics Cloud (SAC), S/4HANA data models, KPI frameworks, reporting, dashboards, self-service BI, and advanced analytics.

• Accountable for requirements and integration management of group-wide SAP BI solutions, including BI standards, data governance, and architecture guidelines.

• Contributed to a global BI transformation program (rollouts, key-user trainings, documentation) to strengthen data literacy and drive continuous improvement.

• Scaled a newly introduced feature from MVP to global rollout within SAP Signavio, reducing customer process modeling time by 40% and increasing NPS from 41 to 63 within two release cycles.

• Re-architected a web application that had grown over years, modularizing tightly coupled components

• Reduced response times from several seconds to <50 ms

• Removed performance bottlenecks

• Simplified architecture so internal teams can implement features on their own again

• Provided expert level consulting for lifecycle, upgrades and refresh activities
• Used Remedy for effort recording and billing to customers
• Used ServiceNow for service management and workflow
• Used Jira for project management with agile/Scrum methods
• Used Confluence for documentation
• Worked with customer-specific software tools
• Worked with customer-provided and secured hardware suitable for IT security operations infrastructure setup for customers
• Built firewall rule sets and handed over to service owner and delivery teams
• Environment: Cisco ASA, Cisco Firepower, CSM, Cisco AnyConnect, Cisco ISE, Check Point VSX and gateways

• Designed and implemented an automation test framework using Junit and Maven, developing BDD scripts with Cucumber and reusable methods for application behavior.
• Created test data using automation scripts with Selenium WebDriver, Java, and Python, validating UI components, popup windows, and mouse movements.
• Conducted API functional testing of RESTful web services using Postman.
• Automated test execution using Maven and integrated with Jenkins, achieving a 20% reduction in regression testing time.