Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Machine Learning Engineer with 3.5+ years of experience progressing from data science into production ML engineering across banking, healthcare, and industrial analytics. Hands-on with Python, PyTorch, scikit-learn, SQL, AWS, Docker, Kubernetes, FastAPI, MLflow, and CI/CD across feature engineering, model training, data pipelines, containerized inference, monitoring, and production troubleshooting. Focused on building reliable, scalable ML systems that improve inference performance, deployment efficiency, data-processing workflows, and operational visibility, partnering with cross-functional teams on root-cause analysis, model changes, governance, and reliability improvements.…Machine Learning Engineer with 3.5+ years of experience progressing from data science into production ML engineering across banking, healthcare, and industrial analytics. Hands-on with Python, PyTorch, scikit-learn, SQL, AWS, Docker, Kubernetes, FastAPI, MLflow, and CI/CD across feature engineering, model training, data pipelines, containerized inference, monitoring, and production troubleshooting. Focused on building reliable, scalable ML systems that improve inference performance, deployment efficiency, data-processing workflows, and operational visibility, partnering with cross-functional teams on root-cause analysis, model changes, governance, and reliability improvements.

ROHIT SAI KIRAN RAVULA

Data Scientist, Data Engineer, AI Engineer, +1





Machine Learning Engineer with 3.5+ years of experience progressing from data science into production ML engineering across banking, healthcare, and industrial analytics. Hands-on with Python, PyTorch, scikit-learn, SQL, AWS, Docker, Kubernetes, FastAPI, MLflow, and CI/CD across feature engineering, model training, data pipelines, containerized inference, monitoring, and production troubleshooting. Focused on building reliable, scalable ML systems that improve inference performance, deployment efficiency, data-processing workflows, and operational visibility, partnering with cross-functional teams on root-cause analysis, model changes, governance, and reliability improvements.…Machine Learning Engineer with 3.5+ years of experience progressing from data science into production ML engineering across banking, healthcare, and industrial analytics. Hands-on with Python, PyTorch, scikit-learn, SQL, AWS, Docker, Kubernetes, FastAPI, MLflow, and CI/CD across feature engineering, model training, data pipelines, containerized inference, monitoring, and production troubleshooting. Focused on building reliable, scalable ML systems that improve inference performance, deployment efficiency, data-processing workflows, and operational visibility, partnering with cross-functional teams on root-cause analysis, model changes, governance, and reliability improvements.

Available to hire

Machine Learning Engineer with 3.5+ years of experience progressing from data science into production ML engineering across banking, healthcare, and industrial analytics. Hands-on with Python, PyTorch, scikit-learn, SQL, AWS, Docker, Kubernetes, FastAPI, MLflow, and CI/CD across feature engineering, model training, data pipelines, containerized inference, monitoring, and production troubleshooting.

Focused on building reliable, scalable ML systems that improve inference performance, deployment efficiency, data-processing workflows, and operational visibility, partnering with cross-functional teams on root-cause analysis, model changes, governance, and reliability improvements.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Language

English

Advanced

Work Experience

Machine Learning Engineer at TD Bank

July 1, 2025 - Present

Develop and refine PyTorch models for financial decisioning workflows in collaboration with data and application engineers. Reworked Dockerized preprocessing and inference paths using batching and execution profiling to reduce average inference latency while maintaining stable API behavior. Hardened Kubernetes-hosted inference with readiness/liveness checks, resource controls, deployment validation, and rollback paths, reducing deployment-related incidents. Added production monitoring for feature distributions, prediction shifts, data-quality failures, latency, and service errors to shorten investigation time. Automated model validation, CI/CD test execution, container builds, and release gates to reduce deployment turnaround and improve release repeatability. Partner with cross-functional teams on root-cause analysis, model changes, technical documentation, governance controls, and reliability improvements.

Machine Learning Engineer at McKesson Corporation

March 1, 2024 - June 30, 2025

Built and evaluated machine learning models for healthcare and pharmaceutical use cases using Python, PyTorch, scikit-learn, and SQL, moving selected approaches toward production-ready workflows. Created reusable feature-generation and training pipelines across millions of structured records to reduce end-to-end data preparation time. Packaged inference components with Docker and supported deployment on AWS and Kubernetes for environment consistency. Exposed model predictions via FastAPI REST endpoints and collaborated on integration with typical online inference response times below 200 ms. Used MLflow for experiment tracking, metric/parameter comparison, artifact management, and model versioning to improve reproducibility and traceability. Added automated schema, data-quality, and model-validation checks to CI/CD workflows to catch regressions before release and reduce recurring deployment issues.

Data Scientist at Solenis

October 1, 2022 - November 30, 2023

Analyzed historical industrial and operational data with Python, SQL, Pandas, scikit-learn, and XGBoost to identify patterns, build predictive features, and support data-driven operational decisions. Built reusable data-cleaning and feature-engineering workflows across multiple operational sources to reduce repetitive preparation effort. Trained and compared predictive models for forecasting and operational risk signals, improving performance through feature engineering, model selection, and hyperparameter tuning. Performed exploratory analysis, cross-validation, error analysis, and feature selection to assess robustness and communicate recommendations. Converted notebook analyses into reusable Python scoring workflows to improve repeatability and support downstream consumption. Investigated data-quality issues with SQL/Python, validated inputs/outputs, and communicated findings to engineering and operations teams.