Shruti Liladhar Devlekar
Data Scientist with 2+ years of experience using Python, SQL, PySpark, and TensorFlow to turn large-scale behavioral and streaming data into actionable insights.
About
Data Scientist with 2+ years of experience using Python, SQL, PySpark, and TensorFlow to turn large-scale behavioral and streaming data into actionable insights. I leverage NLP and Generative AI for improved event classification and content relevance, and I build predictive models to uncover adoption trends and forecast user behavior.
I also design scalable ETL pipelines, segmentation frameworks, and visualization solutions to support better decision-making, operational efficiency, and data-driven product strategy. I’m experienced with AWS, Docker, Kubernetes, and MLflow, and I enjoy building reliable production ML workflows and measurable business impact.
- 2 years' experience
- Joined July 2026
Industry experience
- Telecommunications
- Professional Services
- Software & Internet
- Financial Services
- Healthcare
Work experience
Built real-time event detection workflows using PySpark and AWS SageMaker, improving alert relevance by 18% across global public news and social content streams. Refined NLP classification models using PyTorch and TensorFlow, improving entity extraction consistency by 15% to support faster intelligence assessment for emerging risk events. Engineered feature transformations for streaming data via ETL pipelines, accelerating event ingestion by 24% and improving downstream model readiness. Evaluated Generative AI summaries versus analyst outputs, increasing content relevance by 13% and establishing quality benchmarks. Managed deployment and experimentation using MLflow and Docker, reducing validation turnaround by 16%.
Analyzed Jira and Confluence usage data with Python and SQL to uncover adoption trends, improving feature prioritization accuracy by 14%. Conducted exploratory data analysis on customer interaction datasets, finding 17% variation in engagement behavior across enterprise and mid-market segments. Developed predictive modeling to estimate feature adoption likelihood, improving targeting effectiveness by 12%. Processed behavioral datasets with Apache Spark, reducing feature preparation time by 21%. Created Tableau dashboards to improve stakeholder visibility and centralize adoption insights (18% improvement). Performed model evaluation and statistical analysis to reduce forecasting variance by 17% and strengthen long-term product planning confidence.
Examined campaign performance data using SQL and Power BI to identify audience behavior trends that improved targeted engagement effectiveness by 12%. Integrated customer interaction records across messaging, push notification, and in-app channels, improving reporting completeness by 19%. Used Python (Pandas/NumPy) for data wrangling to reduce segmentation preparation effort by 15%. Validated data quality and attribution reporting outputs, reducing dashboard discrepancies by 16% and improving stakeholder confidence in campaign measurement.
Education
Certifications and awards· 6
Hire Shruti Liladhar Devlekar today
Post a job and invite Shruti, or contact them directly. No hidden commission.





