Sharmisha Yelapati
Professional Summary
AI Platform Engineer with 6 years of experience designing cloud-native data platforms, production-grade Python services, and agentic AI applications. Experienced in building MLOps pipelines, RAG/LLM orchestration, Databricks/Spark processing, streaming systems, and observability across regulated healthcare and financial domains. Delivered solutions processing 20+ TB/day, supported 5M+ healthcare claims/day, and improved release cadence and analytical latency through automation and platform reliability.
Technical Skills
Work Experience
- Engineered integrations and production Python services for an enterprise agentic AI platform (Sierra) used in commercial-card decline voice workflows, improving orchestration reliability for contact-center interactions.
- Owned triage and debugging across agent orchestration, API interactions, and async execution paths, isolating root causes using traces and transcripts to reduce incident triage time.
- Implemented bilingual journey-driven agent behaviors (English/Spanish) using dynamic tool invocation and contextual reasoning to support self-service and human-agent escalation.
- Integrated platform capabilities on GCP with secure gateways, REST interfaces, microservices, telephony systems, and WebSockets across six+ architectural layers to enable real-time voice experiences.
- Established observability across transcripts, traces, tool-invocation logs, and latency telemetry to identify conversational defects, integration failures, and performance bottlenecks.
- Contributed to MLOps readiness and CI/CD across development, staging, and production environments—adding prompt/version governance, simulations, automated validation, and snapshot-based release flows to meet audit requirements.
- Modernized the Payment Accuracy Management ecosystem using Azure Data Factory, Synapse Analytics, and Databricks to process 5M+ healthcare claims daily and accelerate anomaly detection by 40%.
- Designed distributed Python and Spark workloads processing 20+ TB/day with resilient orchestration, retries, and monitoring to sustain 99.9% SLA adherence for critical claims pipelines.
- Operationalized 50+ ML features with MLflow-style versioning and lifecycle governance, enabling production feature stores and controls that contributed to preventing $2M+ in payment leakage.
- Improved release engineering across dev/stage/prod using GitHub Actions, Jenkins, Docker, and IaC, reducing deployment cycles by 40% and lowering release failures.
- Streamlined batch and streaming ingestion using Kafka, PySpark, and Airflow to improve downstream data availability by 35% for analytics and ML consumers.
- Implemented 20+ automated Great Expectations rules and PHI/PII safeguards to reduce production defects by 35% and strengthen HIPAA-aligned audit readiness.
- Spearheaded Spark and Kafka-based processing for 20+ TB of healthcare data, cutting downstream availability delays by 45% for near-real-time analytics.
- Designed AWS-based ingestion and storage patterns using S3 to scale processing across 100+ governed assets and support AI-ready datasets.
- Reengineered dbt transformations for 100+ datasets, introducing modular models and semantic layers that improved delivery efficiency by 30%.
- Automated deployments with Jenkins, GitHub Actions, Docker, Kubernetes, and Terraform to reduce release failures by 40% and accelerate delivery by 50%.
- Centralized observability across lineage, structured logging, and performance telemetry to shorten root-cause analysis by 40%.
- Consolidated feature-ready datasets and reusable models to reduce reporting complexity by 20% and broaden support for predictive healthcare analytics.
- Built 10+ enterprise data marts using SQL and cloud-oriented design patterns, improving financial and regulatory report generation efficiency by 30%.
- Refactored 15+ Python services and ETL workflows to cut execution time by 25% and remove 20+ manual hours/month through automation.
- Leveraged Azure analytics capabilities to support governed financial workloads and improve scalable access to curated datasets for reporting teams.
- Implemented automated anomaly detection checks across regulated financial data to lower reporting discrepancies by 15% and increase downstream trust.
- Produced model-ready datasets for forecasting workflows that improved predictive accuracy by 20% through standardized transformations and validation.
- Accelerated ingestion and business-request fulfillment by 25% using reusable processing components and standardized data access patterns.
- Analyzed customer behavior for 15+ marketing campaigns, improving audience targeting effectiveness by 20% through segmentation and statistical analysis.
- Automated extraction and transformation of 500+ GB of data using Python, eliminating 70% of repetitive manual effort and establishing reusable ETL components.
- Revamped executive dashboards covering 10+ business KPIs to accelerate reporting cycles by 30% and improve stakeholder self-service.
- Improved customer segmentation performance by 15% via feature engineering, exploratory analysis, and statistical modeling.
- Reduced ML data-prep time by 25% through reusable preprocessing and feature-generation frameworks.
- Partnered with cross-functional product teams to translate analytics findings into prioritized product and marketing actions.
- Improved manufacturing throughput by 12% through SQL-driven operational analysis and statistical performance measurement.
- Reduced resource waste by 15% via process studies across three critical production workflows and targeted process changes.
- Modeled industrial datasets using Python and Spark to identify bottlenecks and lower production-cycle duration by 10%.
- Designed predictive-maintenance experiments to surface equipment-reliability insights from structured telemetry and usage data.
- Quantified operational performance across workflow categories to prioritize improvements and enable continuous process monitoring.
- Delivered data-backed recommendations that informed scheduling and resource allocation, improving overall equipment effectiveness.
Education
Achievements
- Databricks Data + AI Summit 2026 — Apps & Agents for Good Hackathon participant — 2026: Completed training in Building Agentic Applications and Deploying & Monitoring Agents on Databricks; demonstrated an agentic healthcare routing prototype.
Powered by Drivetube · Create your own profile at drivetube.ai
Everything on Drivetube
Six products, two of them free forever. Start wherever you are.
Your free digital resume
at drivetube.ai/in/your-name: one true standard resume with a Hiring Snapshot (visa status, expected salary, notice period, work preference, relocation), an ATS-ready PDF download and a single shareable link. Free forever; interview requests come from verified employers and your contact details stay masked until you accept.
Documentation- Free Job BoardFree
Verified jobs, posted in the last 3 days
verified openings crawled ATS-by-ATS from 115,000+ real company career pages across 54 ATS platforms. Shows the true posting date from the source ATS — not when a listing was indexed — and deletes every general listing 3 days after it was actually posted. No ghost jobs, no ad-sponsored listings, no staffing reposts, no account needed.
Documentation - Resume Writing ServicesFrom $25.99
Written by senior career writers
human-written, ATS-optimised resumes by senior career writers, from ₹499.99 / $25.99. Available in every country, written to the destination country's own standard — a US resume, UK CV, German Lebenslauf and Indian resume are genuinely different documents. A paid service, separate from the free Drivetube Profile.
Documentation - Drivetube OneFrom $39.99 / 3 mo
Daily matched jobs, tailored resumes, or we apply for you
Drivetube's paid service. Community sends daily Jobsheets of fresh jobs matched to your profile on WhatsApp and email, with the Drivetube Community ($39.99 for 3 months or $69.99 for 6 months; ₹999 or ₹1,899 in India). Jobhunt is one-time application credits with Community included: one credit tailors one resume and its cover letter (100 for $99 with 3 months of Community, 250 for $199 with 6 months). Let Us Apply is an add-on to Jobhunt: a human expert applies 250 times for you on your credits ($0.60 each, $150). Everything lives on one dashboard at drivetube.ai/drivetubeone.
Documentation - Drivetube HireFree tier
For employers — no job postings, no applications
hiring with no job postings and no applications. Paste your real job description and AI matches it against candidates' true standard resumes, returning ranked candidates with a match %, matched and missing skills and written reasoning. Free tier included; employers pay, candidates never do.
Documentation
- Documentation
every product explained in full, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.
- Playbooks
tactical job-search guides. Each post is one named tactic with the situation it applies to, the exact steps, a copy-paste message and honest failure modes. Free, no account.
The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.
Pricing is identical on the web, iOS and Android — no app-store markup. Monthly Community membership is purchased in the iOS app only; the website sells annual plans. The Android app has no in-app purchase, so Android members subscribe on drivetube.ai and then sign in to the app with full access. Membership follows your account, not your device.