Saivamshi Ausula
Professional Summary
AI Data Engineer with 4+ years of experience specializing in Python, SQL, PySpark, cloud data engineering, ETL, data modeling, and Generative AI solutions across banking, insurance, and healthcare domains. Experienced in building scalable data pipelines, RAG workflows, semantic retrieval, and enterprise analytics platforms, processing 5M+ daily records and improving data-processing efficiency by up to 35%. Brings strong expertise in AWS, Azure, Databricks, Snowflake, data quality, and production-ready AI and data solutions.
Technical Skills
Work Experience
- Engineered RAG pipelines with Amazon Bedrock to retrieve relevant information from internal banking documents, improving grounded responses for enterprise AI applications by 30% and supporting reliable knowledge retrieval.
- Developed banking document processing workflows with Python, transforming unstructured content into structured, searchable datasets that supported downstream AI applications and internal banking knowledge retrieval.
- Optimized semantic retrieval with Amazon OpenSearch, refining search configurations and relevance criteria to reduce irrelevant document matches by 25% across internal banking information workflows.
- Collaborated with data and AI engineering teams to deliver banking data solutions, coordinating development activities team members and supporting reliable production AI applications for business operations.
- Automated banking data transformation with AWS Glue, creating curated datasets for analytics and downstream AI workloads while reducing manual data-processing effort by 35% and improving processing consistency.
- Implemented incremental banking data pipelines with Apache Airflow, incorporating validation and monitoring to improve scheduled workflow reliability and support consistent downstream reporting and analytics.
- Diagnosed schema validation failures and duplicate records across insurance data ingestion pipelines by strengthening Python validation logic, improving the reliability of production policy and claims datasets.
- Accelerated large-scale insurance data processing with PySpark, redesigning partitioning and caching strategies in Azure Databricks to reduce processing time by 30% and improve workload stability.
- Orchestrated incremental and full insurance data loads with Azure Data Factory, implementing metadata-driven scheduling, dependency management, and retry handling to reduce manual pipeline execution.
- Partnered with data engineering and analytics teams to modernize enterprise insurance reporting, supporting dimensional data modeling and coordinating warehouse migration team members, accelerating reporting delivery by 20%.
- Structured curated insurance datasets using Azure Synapse Analytics, organizing policy and claims data for downstream reporting and business analytics while improving accessibility for reporting teams.
- Transformed insurance policy documents with Python and LangChain, cleaning, chunking, and enriching content for RAG-based enterprise search and knowledge retrieval, improving document processing efficiency by 25%.
- Engineered healthcare transaction pipelines with PySpark, processing more than 5 million daily records from Amazon S3 to support finance and operational reporting across multiple business functions.
- Developed reusable healthcare data models with dbt, standardizing transformation logic and improving consistency across downstream reporting datasets used for business analytics.
- Tuned enterprise healthcare workloads with Apache Spark, refining partitioning and caching strategies to reduce overnight batch processing time by 30% and improve workload stability.
- Coordinated with data engineering and reporting teams to support healthcare analytics workflows, contributing to production data initiatives and resolving issues across critical reporting processes.
- Orchestrated healthcare data workflows with Apache Airflow, managing pipeline dependencies and recovery processes to reduce manual production support effort by 35% and improve scheduled workflow reliability.
- Streamlined incremental healthcare transaction ingestion with Amazon Kinesis, enabling curated data delivery for reporting and analytics while supporting consistent processing of operational healthcare data.
- Maintained client data integration workflows by troubleshooting SQL ETL failures, resolving column mismatches and null-value issues to ensure accurate reporting datasets for business operations.
- Automated recurring client data extraction with Python, replacing manual processing across four source systems and reducing weekly preparation time from several hours to approximately 20 minutes.
- Optimized reporting database performance with SQL, restructuring joins and indexing strategies to reduce query execution time by 30% for frequently used business reports.
- Collaborated with senior engineers and reporting teams to troubleshoot client data issues, supporting multiple reporting workflows and improving resolution of production data problems.
- Implemented dataset validation using SQL, identifying null keys, duplicate records, and date-format inconsistencies before data reached management dashboards.
Education
Certifications
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 160,000+ real company career pages across 50+ 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.