About

Models are the easy part. Getting them right is the job.

I'm Chetan, a data scientist and machine learning engineer in Phoenix, with almost five years of building practical ML, deep learning, NLP, computer vision and Generative AI systems across financial services, healthcare and engineering-focused teams, and a Master's in Data Science from UAB.

Right now I'm an ML / AI engineer at Astrion, turning operational, maintenance and telemetry data into something mission and engineering teams can act on: predictive models for equipment events, retrieval over years of engineering documents with RAG and Graph RAG on Neo4j, and GPT-4 / LangGraph workflows that stay tied to approved technical content.

Before that I built fraud and transaction-risk models at PayPal — behavioural features, gradient-boosted classifiers tuned with an eye on false positives, SHAP explanations for risk analysts, and a semantic case search over support text. At Siemens Healthcare I worked on medical image classification and detection, OCR over scanned clinical documents, and semantic retrieval across healthcare records.

The thread through all of it is the full modelling cycle: data preparation and feature engineering at scale with Spark, careful evaluation and explainability, and getting models out of notebooks into FastAPI services with MLflow tracking and CI/CD on AWS, Azure and GCP.

Outside of work I keep a running list of things I don't understand yet and slowly shorten it. Right now that's LLM internals — I've worked through nanoGPT, attention, and induction heads — and radio, which has turned into a LoRa mesh network across the Phoenix West Valley, a satellite pass planner, and an ADS-B receiver that tracks aircraft from my desk.

I'm looking for data science, ML and AI engineering roles, in Phoenix or remote.

Experience

  1. 2025 — Now

    ML / AI Engineer

    Astrion · Huntsville, AL (remote)

    Mission Operations & Engineering Intelligence Platform

    • Built predictive workflows around equipment events and operating conditions with XGBoost, LightGBM and Random Forest, engineering features from historical event and maintenance records and tuning with Optuna and cross-validation.
    • Turned engineering notes, incident descriptions and maintenance comments into usable signals with BERT, spaCy and Sentence Transformers.
    • Built document retrieval with RAG, FAISS, OpenSearch and pgvector, and connected equipment, events and documents in Neo4j for Graph RAG answers a vector-only search would miss.
    • Prototyped GenAI workflows with GPT-4, LangChain and LangGraph, kept answers tied to approved technical content, and traced them with LangSmith.
    • Shipped components as FastAPI services in Docker on AWS (S3, SageMaker, EC2, Glue, Redshift), with MLflow tracking, GitHub Actions CI/CD and SHAP/LIME explanations.

    PythonPySparkXGBoostLightGBMBERTFAISSOpenSearchpgvectorNeo4jGPT-4LangGraphLangSmithFastAPIAWSMLflow

    In detail →
  2. 2023 — 2024

    Machine Learning Engineer

    PayPal · Hyderabad, India

    Transaction Risk, Fraud Detection & Customer Intelligence Platform

    • Designed behavioural features (transaction frequency, amounts, merchant activity, timing, account history) and built fraud and risk classifiers with XGBoost, LightGBM, CatBoost and Logistic Regression.
    • Evaluated with AUC-ROC, precision/recall and confusion matrices with a focus on false positives against legitimate customers; tuned with Optuna, grid and random search.
    • Moved high-volume transaction preparation to Spark / PySpark and reusable SQL + Python routines, so training sets refreshed without manual rework.
    • Added SHAP and LIME explanations for analysts, and built a semantic case search over support text with BERT, Sentence Transformers, FAISS and OpenSearch.
    • Served models through FastAPI and Docker on AWS (S3, SageMaker, ECS, Glue, Redshift), with MLflow tracking and Redis + Celery for async jobs.

    PythonSQLPySparkXGBoostCatBoostSHAPFAISSOpenSearchFastAPIDockerAWSMLflowRedisCelery

    In detail →
  3. 2022 — 2023

    Data Scientist / ML Engineer

    Siemens Healthcare · Hyderabad, India

    Medical Imaging & Clinical Document Intelligence Platform

    • Prepared medical image datasets with OpenCV and trained CNN classifiers in TensorFlow / Keras; explored object detection with YOLO and Faster R-CNN.
    • Extracted text from scanned clinical documents with OCR, Azure Document Intelligence and Azure Cognitive Services.
    • Built clinical text classification with spaCy, NLTK and BERT, and semantic document retrieval with Sentence Transformers and FAISS, prototyping RAG grounded in healthcare documentation.
    • Handled class imbalance and inconsistent images with augmentation and tuning, and used SHAP and error analysis to see where predictions held up.
    • Scaled preparation with PySpark, tracked experiments in MLflow, and served models behind Flask and FastAPI for application teams.

    PythonOpenCVTensorFlowKerasPyTorchYOLOFaster R-CNNBERTspaCyFAISSAzurePySparkMLflowFlask

    In detail →

Education

  1. 2024 — 2026

    M.S. Data Science

    University of Alabama at Birmingham · Birmingham, AL

    Machine learning, computer vision, data engineering, cloud computing, network forensics, algorithms.

  2. Bachelor’s, Data Science

    Vignan Institute of Technology and Science · Hyderabad, India

Projects

Built on my own time, separate from the jobs above.

Skills

Languages
PythonSQLScala
Machine learning
Scikit-learnXGBoostLightGBMCatBoostRandom ForestLogistic RegressionFeature engineeringHyperparameter tuning
Deep learning
PyTorchTensorFlowKerasCNNsLSTMs
Generative AI & LLMs
GPT-4LangChainLangGraphLangSmithHugging Face TransformersBERTSentence TransformersPrompt engineeringReAct
NLP
spaCyNLTKText classificationSemantic searchIntent recognitionDocument processing
Computer vision
OpenCVYOLOFaster R-CNNOCRAzure Cognitive Services
RAG & vector search
FAISSOpenSearchChromapgvectorNeo4jGraph RAGHybrid retrievalCross-encoder reranking
Data engineering
Apache SparkPySparkDatabricksHadoopKafkaAirflowpandasNumPy
Cloud
AWS SageMakerS3GlueRedshiftECSEC2TextractAzure Document IntelligenceGCP BigQueryDataflow
MLOps & deployment
MLflowRAGASDockerKubernetesFastAPIFlaskRedisCeleryGitHub ActionsJenkins
Databases
PostgreSQLMySQLMongoDBSQLAlchemyBigQuery
Evaluation & explainability
OptunaCross-validationSHAPLIMEAUC-ROCConfusion matrix
Visualization & tools
TableauMatplotlibSeabornPlotlyGitREST APIs

Contact

Let's build something.

I'm looking for data science, machine learning and AI engineering roles in Phoenix or remote — and I'm always happy to talk about models, retrieval, or why yours is overfitting.

[email protected] LinkedIn ↗ GitHub ↗