.png){kind=logo}
Ashwitha E
Junior Data Scientist specializing in fraud analytics and cloud data platforms
Connect with Ashwitha
Ashwitha already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Built and deployed production LLM-powered document summarization/classification systems using embeddings, vector databases (RAG-style retrieval), and automated evaluation (BERTScore/ROUGE), with a focus on monitoring and scalable cloud pipelines. Also partnered with a fraud analytics team to deliver a transaction anomaly detection solution, translating model outputs into Power BI dashboards and actionable KPIs while iterating on thresholds and alerts based on stakeholder feedback.
Experience
Education
Key Strengths
- Built and deployed production LLM summarization/classification systems for unstructured text
- Strong evaluation rigor for generative outputs (BERTScore/ROUGE) and automated quality measurement
- Improved summary quality and reduced hallucinations via prompt tuning and constraints
- Data-noise handling through robust preprocessing (cleaning, deduplication, normalization) and output filtering
- Designed scalable, reliable ML/LLM pipelines with model versioning, automated ETL, orchestration, and monitoring
- Hands-on orchestration expertise (Airflow, Azure Data Factory) including DAGs, retries, SLA monitoring, and alerts
- Systematic agent/workflow testing approach (unit + mocked data + end-to-end) with KPIs and fallbacks
- Effective cross-functional delivery with non-technical stakeholders using Power BI, KPIs, and iterative threshold/alert refinement
Discover more candidates like Ashwitha
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent