Tarun Kumar Reddy Nallagari
AI Engineer • New York, NY, USA • n**************@gmail.com • 716****536 • linkedin.com/••••• • drivetube.ai/•••••
Professional Summary
AI Engineer with 4+ years of experience building production machine learning and Generative AI systems across financial services and healthcare. Hands-on with LLMs, Retrieval-Augmented Generation, vector databases, prompt engineering, end-to-end ML pipelines, MLOps, and real-time inference on AWS. AWS Certified Data Engineer with experience operationalizing models in regulated environments and driving audit-ready model governance.
Technical Skills
Programming Languages: Python
Web Technologies: REST APIs
Frameworks and Libraries: LangChain,scikit-learn,PyTorch
Databases: SQL,Snowflake
Cloud and DevOps: Docker,Kubernetes,MLflow,Apache Airflow,AWS SageMaker,AWS Glue,Azure Databricks
Data and Analytics: Feature Engineering,Predictive Modeling,XGBoost
Skills: PySpark
Generative AI & LLM Systems: LLMs,Retrieval-Augmented Generation,Pinecone,FAISS,Embeddings,Prompt Engineering
Work Experience
Ally Financial
New York, USA
AI Engineer
Jul 2025 – Present
Worked at Ally Financial (banking and auto-finance) delivering production ML and Generative AI solutions for credit risk, fraud detection, document processing, and customer support automation.
Tech Stack: Python, LangChain, Pinecone, FAISS, AWS SageMaker, AWS Glue, Docker, Kubernetes, MLflow, Apache Airflow, REST APIs, scikit-learn, XGBoost, PyTorch
- Built Retrieval-Augmented Generation (RAG) pipelines with LangChain and vector DBs (Pinecone, FAISS) to ground LLM responses in enterprise banking documents, improving grounded-response accuracy by 30% for document-processing and customer-support use cases.
- Benchmarked LLM APIs, embedding models, and vector stores and implemented prompt-engineering plus evaluation workflows, reducing hallucinated outputs by 25% in sampled production reviews and guiding vendor/model selection.
- Designed and deployed Python-based production ML models for credit-risk scoring and fraud detection across auto-finance and banking products, increasing detection precision by 20% versus prior rule-based systems.
- Built end-to-end ML pipelines and CI/CD automation using SageMaker, MLflow, and Airflow to manage feature engineering, training, evaluation, and deployment, cutting model release-cycle time by 30%.
- Containerized and served ML models with Docker and Kubernetes on AWS, exposing REST APIs to downstream systems and reducing p95 prediction latency by 25% for low-latency real-time decisioning.
- Implemented model monitoring and drift-detection workflows and automated retraining, aligning with SR 11-7 model governance practices to improve audit readiness and reduce production performance incidents by 25%.
Optum
Bengaluru, India
ai/ ml engineer
Mar 2021 – Dec 2023
Achieved 91% F1-score on ICD-10 entity extraction by developing a clinical NLP pipeline using BioBERT and Hugging Face Transformers to extract diagnoses, medications, and procedures from unstructured physician notes
Tech Stack: Python, PySpark, Apache Spark, Azure Databricks, Snowflake, SQL, Apache Airflow, Hadoop
- Built an HCC risk stratification model using gradient boosting on claims and clinical feature data, lifting risk score accuracy by 22\% and directly supporting Medicare Advantage revenue integrity.
- Reduced manual prior authorization review volume by 38\% by engineering a fine-tuned BERT classification system that automated approval decisions on standard clinical scenarios.
- Orchestrated nightly HCC batch scoring workflows across 2M+ member records using Apache Airflow DAGs, with built-in data quality checkpoints and SLA-compliant failure alerting.
- Designed a PySpark-based ETL pipeline on AWS Glue and S3 to ingest, validate, and transform 10M+ daily clinical records from HL7 and FHIR sources into a Redshift analytics warehouse.
- Streamlined experiment tracking across the clinical AI team using MLflow to log hyperparameters, evaluation metrics, and model artifacts, cutting model reproducibility overhead by 25\%.
- Automated FHIR payload validation and schema enforcement using Great Expectations, reducing production ingestion pipeline failures from malformed data by 60\%.
Education
State University of New York at Buffalo
Master of Science in Data Science • Buffalo, NY • Jan 2024 – Jun 2025
Powered by Drivetube · Create your own profile at drivetube.ai
Explore Drivetube
- Drivetube Profile — 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 Board — verified openings crawled ATS-by-ATS from 100,000+ real company career pages across 35 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.
- Job Hunt Program — managed job hunting, a one-time purchase from $199.99. JobScout matches verified roles to your real experience band, Blend AI writes a uniquely tailored resume and cover letter for every application, and the Autofill extension fills the form — or Let Us Apply submits it for you. Documentation.
- Resume Writing Services — 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.
- Community Membership — from $4.99/month (₹1,999/year in India). Unlocks the gated job-board filters — visa sponsorship, security clearance, workplace and application time — plus Job-Scout AI matching, Resume Report AI, Interview AI prep sheets, Recruiter Outreach AI sent from your own Gmail, Apply or Skip triage, a daily market feed and a $10,000+ library including 23 ATS-validated resume templates. Documentation.
- Drivetube Hire — for employers — 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.
Full product documentation — every product explained, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.
The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.