"Building data pipelines and analytics solutions"
Developed "Talk2Scholars" - Multi-agentic AI framework for 10,000+ academic papers
class DataEngineer:
def __init__(self):
self.name = "Utkarsh Sawant"
self.role = "Data Engineer Intern"
self.company = "Noritual Lab Berlin "
self.education = ["MS Applied Data Science @ SRH Heidelberg",
"BE Computer Engineering @ Mumbai University"]
self.location = "Germany"
self.achievements = ["<1% P&L variance", "80% automation", "40% reliability boost"]
self.current_focus = ["GCP Data Pipelines", "Multi-channel Analytics", "Real-time ETL"]
self.languages_spoken = ["English", "German (A2)", "Hindi", "Marathi"]
def say_hi(self):
print("Thanks for dropping by! Let's brew some data magic together! 🍵✨")
me = DataEngineer()
me.say_hi()
End-to-end pipeline processing 4,000+ daily stock data points with real-time cleaning & GCP automation
ML model analyzing ESG reports & financial sentiment, improving investment decisions by 20%
Multi-agentic framework for academic research with 90% accuracy in extracting key findings
** Academic Excellence:** BE in Computer Engineering (GPA: 8.39/10) | ** Leadership:** President @ SIGCE (Led 50+ team)
Refined Process Quality data needs careful preparation |
Scalable Solutions Building pipelines that grow with needs |
Clean Data Pure insights, no artificial additives |
