class AyushJha:
def __init__(self):
self.role = "AI/ML Engineer & Advanced GenAI Solution Developer"
self.study = "M.Sc. Computer Science @ Universitรคt Paderborn, Germany"
self.current_job = "Working Student โ Technical Consultant @ RealThingks GmbH"
self.previously = "Senior System Analyst (L5) @ InterraIT"
self.location = "Paderborn, Germany"
self.experience = "3+ years"
self.focus_areas = [
"Data Analytics Pipelines (Automotive)",
"Generative AI Solutions",
"LLM-based Applications",
"Multi-Agent Systems",
"RAG Pipelines",
"Cloud & Data Architecture"
]
def current_work(self):
return {
"๐ญ Building": "Data analytics pipelines & AI solutions for global automotive manufacturers",
"๐ฑ Learning": "Advanced LangGraph & CrewAI",
"๐ก Exploring": "Agentic AI & Vector Databases",
"๐ Writing": "Technical blogs on Medium"
}
def tech_stack(self):
return {
"AI/ML": ["LangChain", "LangGraph", "CrewAI", "OpenAI", "Anthropic"],
"Cloud": ["Azure OpenAI", "AWS Bedrock", "Azure ML", "AWS SageMaker"],
"Data Engineering": ["Databricks", "Apache Spark", "ETL/ELT", "Power BI", "Fabric"],
"Backend": ["Python", "FastAPI", "Flask", "Node.js"],
"Frontend": ["React.js", "Next.js", "TypeScript", "Three.js"],
"Databases": ["PostgreSQL", "MongoDB", "Milvus", "ChromaDB", "FAISS"],
"DevOps": ["Docker", "Kubernetes", "Azure DevOps", "GitHub Actions"]
}- ๐ M.Sc. Computer Science @ Universitรคt Paderborn, Germany (April 2026 โ Present)
- ๐ผ Working Student โ Technical Consultant @ RealThingks GmbH (May 2026 โ Present)
- Building data analytics pipelines that turn large-scale automotive data into decision-ready insights for enterprise clients
- Developing and deploying AI-driven solutions for major automotive manufacturers using Python, Databricks, and Spark
- ๐ผ Ex-Senior System Analyst (L5) @ InterraIT (Oct 2025 โ Mar 2026) โ LLM-based systems, agentic AI frameworks, and MLOps platforms
- ๐ผ Ex-Senior Software Engineer โ AI/GenAI @ InterraIT (Jan 2023 โ Oct 2025)
- Delivered AI/ML solutions for global clients including Mercedes-Benz, JCI, and MG
- Built RAG pipelines and a custom multi-agent bot system from scratch
- Improved prediction accuracy by 35% through advanced ensemble ML pipelines
- ๐ 7+ Professional Certifications across Microsoft Azure, Microsoft Fabric, Power BI, and Salesforce
- ๐ "Star Rookie of the Year 2024" & "Promising Junior Award Q4 2023" โ InterraIT
- ๐ 350+ LeetCode Problems Solved โ Consistent problem solver
- ๐ฏ Published Technical Writer on Medium
- "Star Rookie of the Year 2024" โ InterraIT โ recognized for exceptional contributions to AI projects and innovation in Generative AI solutions
- "Promising Junior Award Q4 2023" โ InterraIT โ awarded for technical leadership, innovative problem-solving, and team impact
|
Built from scratch โ a multi-agent architecture with real-time coordination, shared context management, and dynamic routing across complex enterprise workflows. |
Modular GenAI framework with a Milvus vector database, implementing hybrid semantic + keyword retrieval with intelligent re-ranking. |
|
Dynamic data transformation framework with configurable logic, automated validation, and performance-optimized processing for enterprise-scale data pipelines. |
Interactive, bilingual (EN/DE) 3D portfolio built with Three.js and React Three Fiber โ a unique ambient WebGL scene behind every section. |
- ๐ Building Production-Ready RAG Pipelines with LangChain
- ๐ค Multi-Agent Systems: The Future of AI Applications
- โ๏ธ Azure OpenAI vs AWS Bedrock: A Comprehensive Comparison
- ๐ก The 15 Most Common Mistakes Web Developers Make
โก๏ธ More articles on Medium...
๐ก "Building the future with AI, one line of code at a time."
โญ๏ธ From A-jha383 with โค๏ธ



