.png){kind=logo}
Priyanshu Maurya
Mid-level Data Scientist specializing in insurance, finance, and healthcare analytics
Connect with Priyanshu
Priyanshu 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 productionized LLM-driven sentiment scoring for earnings call transcripts at Goldman Sachs, replacing legacy NLP to deliver a cleaner trading signal while managing latency/cost via batching, caching, and distilled models. Also implemented an Airflow-orchestrated fraud modeling pipeline at MetLife with drift-based retraining and SageMaker deployment, and has a disciplined evaluation/rollout framework for reliable AI workflows.
Experience
Education
Key Strengths
- Deployed LLM-based sentiment scoring system for earnings call transcripts in production (Goldman Sachs)
- Optimized LLM system for latency and cost using batching, caching, and distilled models
- Uses operational metrics (p50/p95 latency, end-to-end scoring time) to measure performance
- Built Airflow-orchestrated fraud model pipeline with drift-triggered retraining and SageMaker deployment (MetLife)
- Structured reliability approach for AI workflows: guardrails/fallbacks plus offline → sandbox → controlled rollout testing
- Balances quantitative evaluation (success rate, errors, latency, escalation) with qualitative user/stakeholder feedback
- Selects models and retrieval methods based on complexity/latency/cost; applies embedding retrieval for nuanced unstructured text
Discover more candidates like Priyanshu
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent