Data Scientist / ML Engineer · Bangalore, India

I build ML and AI systems that solve real problems,
for businesses and for people.

~3 years shipping Machine Learning models, GenAI pipelines, and automation systems — from $20M+ in claims savings at a healthcare analytics firm to cutting multi-day workflows down to minutes for fintech and energy clients. Currently freelancing as an independent AI consultant.

95%Faster tax documentation generation through automation
320 → 17SDoH features selected with improved model performance
$20M+Contract savings surfaced for large health plans
5+Domains with Shipped Systems
01 — Selected projects

Things I’ve built

Personal projects where I owned the whole thing — data, model, and the interface someone actually uses.

  1. 01Skin Relief & Color Correction ToolShipped2025Built to solve a problem I was actually dealing with — visible facial redness from eczema that most photo tools either ignore or oversmooth into something fake-looking. Detects redness and skin texture and corrects it subtly, in-browser, with nothing ever leaving your device.React 18TypeScriptTailwind CSSHTML5 CanvasVite
  2. 02ICP Lead Gen EngineShipped2026An evidence-first lead generation pipeline: every fit score is computed in code, and every cited signal is re-verified against its source before a lead is shown — grounded evidence outranks a high LLM confidence score, not the other way around.PythonClaude (Sonnet + Haiku)Claude CodeApollo APITavily API
  3. 03Bidirectional Style Translation EngineShipped2024A fine-tuned lightweight LLM that translates English between modern, Gen-Z, and Shakespearean registers in both directions — built around a hand-engineered, API-augmented dataset and a training loop that fits in Colab.PythonHugging Face TransformersGoogle Gemini APIGoogle Colab
  4. 04Satellite Land ClassificationArchived2023A big-data pipeline that processes multi-source satellite imagery with PySpark and runs supervised models for multi-class land classification, reaching 73.2% accuracy.PythonPySparkscikit-learnXGBoostMatplotlib
  5. 05LiftVisionIn progress2026Computer vision pipeline that analyzes lifting biomechanics from video and automatically flags technique inconsistencies.PythonMediaPipe
02 — Experience

Where I’ve worked

  1. Nov 2025 Present

    Independent AI ConsultantF&D Partners / QapitaCurrent

    Freelance LLM pipeline, automation, and analytics consulting — a fintech cap-table platform, then a deregulated-energy advisory firm.

    • F&D Partners — energy advisory · Jun 2026 – Present
      • Building in automations to cut down on manual processing for analysts and users on the customer facing portal.
      • Automated supplier evaluation, cutting a 3-hour manual analytics process to minutes
      • Combined agentic browsing with custom Python workflows for real-time data extraction
    • Qapita — fintech / cap-table platform · Nov 2025 – May 2026
      • Built a multi-jurisdiction document automation pipeline across 15+ regulatory contexts, processing 10,000+ records and cutting report generation time by 95%
      • Developed an LLM-based data migration pipeline with deterministic fallbacks for non-standard fields — zero data loss across full dataset transfers, cutting onboarding from days to hours
      • Instrumented 200+ Mixpanel events across 5 core product workflows, generating insights that directly influenced product roadmap decisions
    PythonLLM PipelinesRAGAgentic AIDockerAutomation EngineeringFintechEnergy AdvisoryProduct Analytics
  2. Jul 2025 Oct 2025

    ML Engineer — GrowthMason

    Growth-focused ML pipelines for sales and marketing teams.

    • Built a Python ETL pipeline aggregating multi-source social media data for ad-hoc data collection and analysis
    • Automated data collection and normalization for sales stakeholders, improving lead-gen productivity by 50%
    • Created a content analysis and personalization pipeline using Gemini Vision, reduced internal manual workload by 75%
    PythonETLGemini VisionGrowth AnalyticsPlaywrightGTM
  3. Nov 2023 Mar 2025

    Junior Data Scientist — Healthcare AnalyticsCertilytics Inc.

    Deep learning and statistical modeling on claims data for Fortune 500 health plans.

    • Delivered up to $20M in contract savings by engineering deep learning anomaly detection on claims data
    • Reduced model input dimensionality from 320 to 17 features (95% reduction) via unsupervised feature extraction while improving predictive accuracy, and reducing bias
    • Automated client deployment recalibration, cutting new client setup time by 71%
    • Refactored a Scala/SQL data pipeline, cutting error rate 30% and runtime 40%
    PythonPyTorchScalaSQLAnomaly DetectionDeep LearningHealthcare AnalyticsFeature EngineeringMLOps
  4. Jun 2021 Aug 2021

    Data Science Intern — Business IntelligenceView, Inc.

    Built a predictive model to flag potentially malfunctioning smart-glass units in the field before customers noticed.

    • Designed a KNN model on sensor data to flag failing insulated glass units with 78% accuracy.
    • Automated collection, cleaning, and analysis of Splunk data via Python and MySQL.
    PythonSQLStatisticsBI
  5. Aug 2020 May 2023

    Lecture Assistant & Grader, CMPSC 221Penn State — College of Engineering

    Object-oriented programming with web design (Java). Held office hours coaching 300+ students.

    JavaTeaching
03 — About

Short version

I’m a data scientist and ML engineer with a B.S. from Penn State and a couple years bouncing between healthcare, fintech, and energy. At Certilytics I built deep-learning anomaly detection on healthcare claims data (helped save health plans $20M+); since then I’ve moved into freelance AI consulting, building LLM pipelines and automation systems for fintech and energy clients — deliberately choosing the consulting model to work across more problems, faster, than one role would let me.

Outside of work I’m usually strength training, playing padel, or messing around with some LLM side project that has no business plan attached. I also enjoy reading so if you have any book recommendations you'd like to share, drop me a message!

04 — Recommendations

What colleagues say

He developed deep learning models to extract nuanced contract-optimization opportunities in large-scale healthcare claims data, and played a key role in researching improvements like automated model calibration. Sriram took the initiative to learn new technologies and languages to support his work.
Eugene KwakSVP, Data ScienceCertilytics
Sriram excelled at translating complex analytic results into clear, actionable insights for both technical and non-technical stakeholders, and integrated seamlessly into our team’s collaborative culture.
Dr. Robert DwyerEVP & Chief of Data ScienceCertilytics
Enthusiastic and curious — key requirements for a student interested in engineering research. Sriram was exposed to cutting-edge work at the Laboratory for Hypersonic and Shock Wave Research and completed a project of his own while there.
Prof. K.P.J. ReddyChair Professor, HALDept. of Aerospace Engineering, IISc Bangalore

Let’s talk.

I’m open to Data Scientist, ML Engineer, and AI/GTM Engineer roles at teams that ship. Also open to short-term consulting engagements if you need something built fast. The fastest way to reach me is email — I read everything.

sriramkiyengar@gmail.com