Priyanshu Shekhar Sinha

Lead the design and development of an enterprise RAG platform spanning ingestion, retrieval, ranking, and access control across cloud providers.

• Architecting scalable distributed-database solutions via Citus DB research and implementation for enterprise-scale workloads.
• Mentoring cross-functional team on robust data pipelines, complex LLM fine-tuning challenges, and enterprise deployment strategies.
• Collaborating with senior leadership on strategic product development and onboarded the first enterprise client for the Text2SQL solution.
• Evaluating emerging protocols like MCP for enterprise connectors.

Foundational AI engineering on Discover — Elastiq's flagship product — covering fine-tuning, retrieval, and agent design.

• Fine-tuned LLaMA 3.1 70B via advanced QLoRA and LoRA techniques, reaching 85% target accuracy.
• Built the foundational Text2SQL framework from scratch and shipped AI agents for natural-language to SQL plus unstructured file processing.
• Integrated multiple Graph DB backends offering Classic RAG, Cypher-based RAG, and GraphRAG — extending Discover with structural retrieval.
• Engineered custom datasets and context-aware chunking algorithms for unstructured-document RAG performance.

Senior Data Scientist at a research, analytics, and technology partner to the financial services sector — asset managers, investment banks, private equity, hedge funds, and consulting firms.

• Developed a versatile analysis dashboard for an investment firm enabling KPI monitoring and analysis experiments — 87% reduction in client analysis time.
• Built a web dashboard integrated with an ESG data engine for a top-tier investment firm, shaping their investment-strategy decisions.
• Shipped an end-to-end RAG system for parsing financial reports.

• Led a 5-person team shipping a flexible A/B Testing Framework for a leading pharmaceutical client to measure promotion success against revenue lift.
• Co-led a 7-person team on a sales-anomaly flag pipeline accounting for seasonality — drove customer outreach delivering +$125K revenue in Q1.
• Built an LSTM model forecasting customer return-to-purchase windows for supply and demand balancing — R² 0.9012.

• Reduced new-client integration from 10 days to 3 hours (97% improvement). Operational reports from 5 days to 30 minutes; opportunity reports from 1 day to 30 minutes.
• Reduced advanced-analytics report generation from 7 days to 15 minutes (99% improvement). Automated Power BI dashboard refreshes.
• Awarded Star Performer of the Month.

• Designed a multi-phase pipeline enriching extracted document data points — generated 500+ features via NLP, data wrangling, and text mining.
• Co-developed a matrix-multiplication ensemble on the NumPy stack across 10+ unique sources for entity classification, plus custom Bayesian models for word embeddings.
• Shipped end-to-end claims-document pipelines for automobile and healthcare enterprise clients; built a geometric model for tabular-entity extraction using asymmetric graphs.

• Mentored college students and working professionals transitioning into data science — career strategy, project review, and mock interviews for analytics and ML roles.