Komal Kumar Penti
Professional Summary
Data Scientist with 4 years of experience designing and productionizing analytics, machine learning, and Generative AI solutions for healthcare and insurance. Strong hands-on expertise in Python, SQL, PySpark, XGBoost and explainability tooling (SHAP) to build classification and regression models for claims, underwriting, and utilization workflows. Experienced building secure RAG applications and LLM assistants using LangChain, sentence-transformer embeddings and FAISS, and integrating EHR/claims/ADT/prior-authorization sources. Proven delivery of production scoring via SageMaker, FastAPI, and MLflow plus operational monitoring with CloudWatch and drift detection. Skilled at feature engineering, entity resolution, and building Power BI dashboards (with DAX) to operationalize ML insights while enforcing HIPAA and PHI controls for clinical review and fraud detection workflows.
Technical Skills
Work Experience
- Partnered with utilization-management nurses, medical directors, and product teams to surface documentation gaps and prioritize analytics, ML, and RAG solutions tied to authorization-review pain points.
- Defined and prioritized data-science use cases for documentation completeness and authorization risk, translating clinical requirements into measurable model objectives and evaluation criteria.
- Built member-level datasets by integrating claims, eligibility, provider, EHR, laboratory, ADT, and prior-authorization records using PySpark and AWS Glue to support downstream Health OS workflows.
- Delivered Power BI dashboards (with DAX measures) for authorization volume, denial reasons, missing documentation, and turnaround time; helped clinical teams identify bottlenecks and contributed to a 61% reduction in insufficient-information denials.
- Designed a secure LLM-powered RAG application using LangChain and sentence-transformer embeddings to retrieve source-grounded clinical notes and medical-policy evidence during authorization reviews.
- Implemented a FAISS-based vector store with metadata filters to enable fast, citation-aware retrieval while enforcing source citations and scoped access to PHI.
- Developed XGBoost models to predict authorizations likely to require additional documentation and applied SHAP to produce reviewer-facing explanations and subgroup calibration checks.
- Productionized batch and real-time scoring using SageMaker and FastAPI and instituted model versioning and experiment tracking via MLflow with operational alerts through CloudWatch.
- Built ETL pipelines using AWS Glue and Python to ingest claims, policy, customer, provider, and payment data into S3 while applying entity-resolution rules to link provider and customer records.
- Implemented 25+ automated data validation checks in Glue jobs and SQL that reduced recurring manual data review by approximately 28%.
- Engineered a reusable feature library using Pandas and NumPy covering claim frequency, prior losses, policy tenure, provider concentration, duplicate submissions, and payment behavior.
- Developed suspicious-claim classification models using XGBoost and Random Forest with stratified cross-validation and class weighting to address imbalanced labels and reduce false-positive reviews.
- Built regression models for claim-severity prediction using Random Forest and applied SHAP explanations to support claims specialists in case review.
- Created a proof-of-concept LLM knowledge assistant for policy and underwriting teams using OCR and semantic chunking with vector search and prompt grounding to interpret policy documents while enforcing citations and PII masking.
- Enabled model deployment and downstream usage via SageMaker batch jobs and FastAPI endpoints and tracked experiments and model artifacts with MLflow and Git for reproducibility.
Projects
- Built a hackathon-winning RAG-based career assistant that securely analyzes resumes and job postings using LLMs, vector search, and automated document processing.
- Implemented privacy-aware PII detection and OCR for resume ingestion and used embeddings and nearest-neighbor search for personalized recommendation generation.
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 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.