Sayali – Data Science Expert –  10+ years Exp – Our own H1B – Local to Bay Area CA – Willing to relocate anywhere in USA

Sayali – Data Science Expert –  10+ years Exp – Our own H1B – Local to Bay Area CA – Willing to relocate anywhere in USA

Sayali's Resume

 

Results-driven Analytics Engineer and Data Science Expert with around 10 years of progressive experience architecting scalable data pipelines, ML-integrated workflows, and executive-grade BI solutions across healthcare, fintech, IoT, supply chain, and infrastructure domains. Expert-level proficiency in Python, SQL, and Snowflake with deep hands-on expertise across AWS, GCP, Azure, dbt, Apache Spark, Kafka, and Airflow. Proven track record delivering measurable impact — surfacing $20M+ in capacity opportunities, identifying $350K+ in financial discrepancies, and architecting HIPAA-compliant healthcare data products at scale. ★ Intuit Hackathon winner; recognized for AI/ML integration, executive data storytelling, and cross-functional leadership across regulated industries (HIPAA, SOX, PCI-DSS).

★  Intuit Internal Hackathon Recognition — Workforce & Revenue Analytics BI Platform — Intuit, 2025

Architected a semantic-layer BI platform on Databricks and GCP BigQuery adopted organization-wide for C-suite scenario modeling; surfaced $20M+ in capacity optimization opportunities — recognized as highest-impact delivery of the quarter by senior engineering and product leadership.

★  iPSH Product Delivery Award — On-Time, In-Full — Intellect Design Arena

Recognized for successful on-time, in-full delivery of the iPSH digital payment product; engineered cloud-integrated ETL/ELT pipelines, Snowflake data warehousing, and payment processing analytics for 15+ global banking clients.

★  MS Capstone: Asclepius — FDA Breakthrough Therapy & Market Access Analytics — 2022

Graduate capstone analyzing FDA oncology breakthrough therapy drugs using US Census Bureau datasets; demonstrated advanced predictive modeling and data storytelling to translate complex regulatory data into strategic market intelligence.

Analytics Engineer  /  Revenue Data Quality Expert     Jul 2025 – Present

Cambia Health Solutions  —  Healthcare Data Engineering & Revenue Analytics  |  Snowflake · dbt · Python · Spark · Kafka · Airflow · AWS · Streamlit · Sigma

• ★ AI/LLM Integration — Recognized by Leadership: Led cross-functional initiative integrating AI agents and LLMs into the Supplemental Data Quality Framework on Snowflake and AWS; architected connections between dbt transformation layers, LLM analysis engines, and Sigma visualizations for intelligent anomaly detection and executive reporting — recognized by product and engineering leadership as a strategic differentiator for operationalizing AI-powered data intelligence at scale.
• Engineered HIPAA-compliant ETL/ELT pipelines on Snowflake, AWS (S3, Glue), and Apache Spark processing healthcare EMR/EHR data including HL7/FHIR-formatted claims, encounter, and provider records — improved pipeline reliability by 30% and reduced monthly data validation overhead by 8 hours.
• Architected the Provider One data product, extracting and transforming clinical provider data from EPIC EHR into a governed Snowflake dimensional model using dbt — enabling 12+ care coordination teams to execute targeted patient interventions across 8,000+ patient records.
• Designed the Supplemental Data Quality Framework using Python, Apache Spark, and Airflow orchestration to surface revenue-impacting data errors — drove measurable revenue improvement for the product and reduced end-user error rates by 35%.
• Implemented real-time streaming pipelines using Apache Kafka and Spark Streaming for Medicare/Medicaid managed care analytics — reduced data latency from batch (T+1) to near-real-time, directly supporting revenue analytics and executive reporting for C-suite stakeholders.
• Built interactive Streamlit and Sigma dashboards translating complex healthcare revenue and data quality metrics into executive data stories — enabling data-driven decision-making for finance and operations leadership across Medicare and Medicaid product lines.
• Established data governance and security frameworks compliant with HIPAA/PHI and HL7/FHIR standards — implemented schema validation, data lineage tracking, and access control policies across Snowflake environments, reducing audit risk and PHI exposure.

Sr. Analytics Engineer  /  Data Science Expert           Feb 2025 – Jul 2025

Intuit (Contract)  —  FinTech — QuickBooks & TurboTax  |  GCP · BigQuery · Azure · Databricks · Snowflake · Spark · Airflow · dbt · Qlik Sense · Tableau · GitLab · SOX · PCI-DSS

• ★ Intuit Hackathon Winner — Architected an executive BI platform integrating workforce allocation, revenue forecasting, and GTM capacity modeling on Databricks and GCP BigQuery; surfaced $20M+ in capacity optimization opportunities — dashboard adopted by C-suite for quarterly strategic planning and recognized as highest-impact delivery of the quarter by senior engineering and product leadership.
• Designed a Tableau Capacity Calculator connecting 25+ global GBSG teams across QuickBooks and TurboTax product lines — standardized annual and quarterly planning KPIs for executive decision cycles, reducing ad-hoc reporting requests by 40% and accelerating C-suite decision velocity by 3–5 business days.
• Engineered GCP Pub/Sub event-driven ingestion pipelines and Snowflake ELT workflows consolidating Workday, iCIMS, and Salesforce data using Apache Airflow and Apache Spark — delivered 30% reduction in forecast cycle time and 18% improvement in workforce and revenue forecast accuracy.
• Built a governed semantic layer using LookML and dbt standardizing KPI definitions across Finance, Operations, and GTM for 50+ executive dashboards — improved KPI consistency by 35% and eliminated conflicting metric definitions across C-suite reporting.
• Integrated AI/ML tooling (Python, scikit-learn, LangChain) into anomaly detection pipelines — reduced root-cause investigation time by 70% and demonstrated hands-on exposure to LLM integration, RAG pipelines, and predictive analytics within a regulated FinTech data platform.
• Maintained SOX and PCI-DSS compliance across all pipeline and dashboard environments — established data quality SLAs at 99%+ freshness and deployed CI/CD pipelines via GitLab for zero-downtime Spark releases on GCP and Azure/Databricks.
• Remediated legacy Looker/LookML dashboard performance issues across 12+ dashboards — achieved 40% reduction in refresh latency and 100% SLA compliance for QuickBooks payment and revenue reporting environments.
• Trained and guided 3 data analytics interns on BigQuery SQL optimization, Tableau development, Qlik Sense reporting, and Agile delivery practices — increasing team delivery capacity within a 90-day cycle.

Data Science Engineer  /  Project Controls                 Jan 2023 – Jan 2025

Charge EPC  —  Infrastructure & Energy  |  SAP · AWS · Power BI · Delta Lake · Terraform · Viewpoint Vista · Precon · Python · SQL · Advanced Excel

• ★ CFO Partnership & Strategic Impact — Served as primary analytics partner to CFO and Finance leadership, architecting financial reporting and forecasting data models for a $500M+ infrastructure portfolio (PG&E, SoCal Gas, ChargePoint) on AWS (S3, Glue, Redshift) — designed Python/SQL predictive forecasts enabling $50M+ in data-driven contract approvals and reducing month-end close by 5 days.
• Led ERP integration and transition from legacy Viewpoint Vista and Precon systems to SAP — documented 40+ BRD/FRD requirements, engineered ETL/ELT migration pipelines on Delta Lake (AWS), and integrated AI-assisted Python classification models (scikit-learn) to auto-tag cost-code records, reducing manual remediation by 65%.
• Proactively identified $350K+ in cross-entity underbilling and overbilling discrepancies via high-granularity SQL anomaly detection across Foundation and SAP datasets — implemented permanent reconciliation procedures on AWS RDS reducing audit adjustments by 90%.
• Built Power BI executive dashboards and automated Python alerting workflows monitoring Earned Value Management (EVM) metrics (SPI/CPI), budget burn rates, and subcontractor billing anomalies in real time — reduced manual report assembly from 40 hours to 4 hours/month and escalation response time by 60%.
• Engineered predictive analytics models (Python, scikit-learn) tracking schedule variance and cost performance index across high-risk PG&E and SoCal Gas infrastructure projects — prevented $2M+ in projected cost overruns across 3 project sites through proactive data-driven intervention.
• Designed Terraform-managed cloud infrastructure supporting production analytics pipelines on AWS — standardized deployment processes and reduced environment provisioning time by 50% while enforcing data governance, security, and access control best practices.
• Mentored and guided 2 junior analysts on AWS SQL query optimization, Power BI DAX modeling, and data governance best practices — improving team throughput and reporting quality within a 6-month period.

Data Analyst                                                             May 2022 – Dec 2022

B2U Storage Solutions  —  Supply Chain & EV Battery Asset Management  |  Python · SQL · IoT · dbt · Tableau · ML · Databricks · Big Data

• Architected an end-to-end IoT data pipeline and inventory performance ticketing tool using Python, SQL, and dbt on Databricks — ingesting telemetry from 500+ EV battery assets across PG&E, SoCal Gas, and ChargePoint deployments; reduced report generation from 6 hours to 15 minutes and improved asset operations visibility by 30%.
• Developed predictive analytics and ML models (Python, scikit-learn) for battery State-of-Health (SoH) scoring and failure pattern detection across 500+ second-life EV batteries — extended average battery cycle life by an estimated 12% and generated $150K+ in annual maintenance savings.
• Designed a scalable data warehouse on Databricks consolidating IoT telemetry, CMMS maintenance, and procurement datasets through big data processing and data mining techniques — enabled real-time monitoring for 500+ assets, reducing reporting latency from weekly to real-time for C-suite operational decisions.
• Built Tableau executive dashboards translating operational telemetry and supply chain KPIs into actionable performance analytics — established data warehousing integrity standards supporting multi-source asset intelligence for energy sector clients (PG&E, SoCal Gas, ChargePoint).
• Collaborated with C-suite and executive stakeholders to deliver data-driven insights on asset performance and inventory optimization — supporting strategic investment decisions for second-life EV battery technology in the semiconductor and energy domain.

Product Engineer                                                       Dec 2017 – Sep 2020

Intellect Design Arena Ltd.  —  FinTech / Banking & Insurance SaaS  |  Cloud · Snowflake · Airflow · Python · SQL · dbt · ETL/ELT

• ★ iPSH Delivery Award — Recognized for on-time, in-full delivery of the iPSH digital payment product; engineered cloud-integrated ETL/ELT pipelines and Snowflake data warehousing solutions for 15+ global banking clients across the full payment lifecycle (authorization, settlement, dispute resolution, reconciliation).
• Built Python/SQL analytics engines surfacing $2.5M in monthly payment processing anomalies across multi-source transaction datasets — improved client revenue retention by 22% and reduced chargeback resolution time by 40% through dbt-powered transformation models.
• Designed cloud-based data warehousing and dimensional data models for PCI-DSS-compliant payments processing, tokenization, and fraud detection — reduced reconciliation cycle from 3 days to overnight through automated Airflow-orchestrated ETL/ELT quality checks and schema validation.
• Optimized SQL query performance by 45% through index tuning and partitioned table design across cloud integration layers — enabling real-time visibility for banking leadership on fraud trends, settlement performance, and dispute rates across APAC and MENA markets.

Business Data Analyst                                                Jan 2016 – Dec 2017

Globuzz Media  —  Digital Marketing Analytics  |  SQL · dbt · Power BI · Advanced Excel

• Designed clickstream and customer behavior analytics models using SQL, dbt, Power BI, and Advanced Excel for AdTech clients — improved audience targeting efficiency by 20% through data-driven business analytics and media strategy recommendations synthesized from multi-source digital marketing datasets with client collaboration.

MS in Business / Data Analytics  |  California State University, East BayDec 2022

Post Graduate Diploma in Advanced Computing  |  University of PuneDec 2016

Bachelor of Computer Engineering  |  University of PuneJun 2016

Languages & Programming:  SQL (Expert — Snowflake, BigQuery, Redshift, Oracle, Hive/Presto | Advanced CTEs, Window Functions, Query Optimization), Python (Pandas, NumPy, Scikit-learn, PySpark, LangChain, Streamlit, Automation Scripting), Scala, R, Bash

Cloud & Data Platforms:  AWS (S3, Glue, Redshift, Lambda, SageMaker, EC2, RDS), GCP (BigQuery, Pub/Sub, Dataflow, Cloud Storage, Vertex AI), Azure (Data Factory, Synapse, Databricks, DevOps), Snowflake, Delta Lake, Oracle ERP, SAP, DynamoDB, MongoDB

Data Engineering & Pipelines:  ETL/ELT Pipeline Architecture, Apache Spark, Apache Kafka (Real-Time Streaming), Apache Airflow (Orchestration), dbt (Transformation, Testing, Lineage), CI/CD (GitLab, GitHub Actions), Terraform, DataOps, Data Lake Architecture

Data Warehousing & Storage:  Snowflake, BigQuery, Databricks (Delta Lake), Amazon Redshift, Azure Synapse, Oracle ERP, SAP, SQL Server, PostgreSQL, MongoDB, NoSQL, Data Vault Modeling

AI / ML & Generative AI:  Scikit-learn, TensorFlow, PyTorch, BigQuery ML, LangChain, OpenAI API, RAG Pipelines, Prompt Engineering, Vector Databases (FAISS, Pinecone, Chroma), Anomaly Detection, Predictive Modeling, LLM Integration, AWS SageMaker

BI & Visualization:  Tableau (Development, Migration, Validation), Power BI (DAX, Power Query, Advanced Modeling), Looker / LookML (Semantic Layer), Qlik Sense, Sigma Computing, Streamlit, SSRS, Advanced Excel

Data Governance & Compliance:  HIPAA / PHI Compliance, PCI-DSS, SOX, HL7 / FHIR, Data Lineage, Great Expectations, Schema Validation, Audit Controls, Data Quality SLAs, Data Catalog, GDPR, PII Protection

Domain Expertise:  Healthcare (EMR/EHR, EPIC, HEDIS, Medicare/Medicaid, HL7/FHIR), FinTech & Digital Payments, Revenue Analytics & FP&A, IoT & Asset Analytics, Infrastructure & Energy, Supply Chain Operations, Executive Stakeholder Management

 

 

Kushal Desai