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

AI/ML Engineer with 6+ years of experience shipping production machine learning, NLP, and generative AI systems across banking, energy, and consulting. Hands-on across the full ML lifecycle—data pipelines, model development, deployment, and monitoring—using Python, PyTorch/TensorFlow, Spark, and cloud platforms. Proven track record building fraud detection, document intelligence (LLM/RAG), and time-series forecasting systems that deliver measurable business impact. Experienced in MLOps with MLflow, Docker, Kubernetes, Airflow, and FastAPI, along with model monitoring, drift detection, and explainable AI for risk/compliance review.…AI/ML Engineer with 6+ years of experience shipping production machine learning, NLP, and generative AI systems across banking, energy, and consulting. Hands-on across the full ML lifecycle—data pipelines, model development, deployment, and monitoring—using Python, PyTorch/TensorFlow, Spark, and cloud platforms. Proven track record building fraud detection, document intelligence (LLM/RAG), and time-series forecasting systems that deliver measurable business impact. Experienced in MLOps with MLflow, Docker, Kubernetes, Airflow, and FastAPI, along with model monitoring, drift detection, and explainable AI for risk/compliance review.

Ruchita Chirumamilla

AI Engineer, Data Scientist, Data Engineer, +4





AI/ML Engineer with 6+ years of experience shipping production machine learning, NLP, and generative AI systems across banking, energy, and consulting. Hands-on across the full ML lifecycle—data pipelines, model development, deployment, and monitoring—using Python, PyTorch/TensorFlow, Spark, and cloud platforms. Proven track record building fraud detection, document intelligence (LLM/RAG), and time-series forecasting systems that deliver measurable business impact. Experienced in MLOps with MLflow, Docker, Kubernetes, Airflow, and FastAPI, along with model monitoring, drift detection, and explainable AI for risk/compliance review.…AI/ML Engineer with 6+ years of experience shipping production machine learning, NLP, and generative AI systems across banking, energy, and consulting. Hands-on across the full ML lifecycle—data pipelines, model development, deployment, and monitoring—using Python, PyTorch/TensorFlow, Spark, and cloud platforms. Proven track record building fraud detection, document intelligence (LLM/RAG), and time-series forecasting systems that deliver measurable business impact. Experienced in MLOps with MLflow, Docker, Kubernetes, Airflow, and FastAPI, along with model monitoring, drift detection, and explainable AI for risk/compliance review.

Available to hire

AI/ML Engineer with 6+ years of experience shipping production machine learning, NLP, and generative AI systems across banking, energy, and consulting. Hands-on across the full ML lifecycle—data pipelines, model development, deployment, and monitoring—using Python, PyTorch/TensorFlow, Spark, and cloud platforms.

Proven track record building fraud detection, document intelligence (LLM/RAG), and time-series forecasting systems that deliver measurable business impact. Experienced in MLOps with MLflow, Docker, Kubernetes, Airflow, and FastAPI, along with model monitoring, drift detection, and explainable AI for risk/compliance review.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Language

Work Experience

Senior AI/ML Engineer at Barclays

May 1, 2024 - Present

Designed and deployed fraud detection and financial risk scoring models (XGBoost, deep learning ensembles) on multi-million-row transaction datasets, improving fraud identification accuracy by 28% and cutting false positives by 22%. Built an LLM-based document intelligence solution using Hugging Face transformers and retrieval-augmented generation (RAG) to extract insights from loan narratives and compliance documents, reducing manual review effort by 45%. Implemented real-time anomaly detection for transaction monitoring, surfacing suspicious activity 30% faster than the legacy rule-based system it replaced. Productionized models with FastAPI, Docker, Kubernetes, and MLflow, cutting deployment turnaround from weeks to days and standardizing the team’s release process. Introduced automated model monitoring and drift detection pipelines. Partnered with risk and compliance teams to deliver explainable AI (SHAP-based) documentation and accelerated adoption across business units. Mentore

AI/ML Engineer at Shell Petroleum

December 1, 2021 - August 31, 2023

Built predictive maintenance models on IoT sensor data using gradient boosting and LSTM networks, reducing unplanned equipment downtime by 26%. Developed time series forecasting models for demand planning and operational optimization, improving forecast accuracy by 24% over incumbent baselines. Engineered large-scale batch and streaming data pipelines with PySpark and Databricks, cutting data preparation time by 40% for downstream ML workloads. Designed anomaly detection frameworks to flag early signs of equipment failure, reducing maintenance response times by 32%. Applied NLP to maintenance logs, inspection notes, and technical documents to improve information retrieval and reduce manual analysis effort. Deployed containerized models to the cloud, reducing inference latency by 20%, and automated Power BI dashboards for operations teams.

ML Engineer at Deloitte

June 1, 2019 - November 30, 2021

Delivered ML solutions across client engagements including churn prediction, customer segmentation, and demand forecasting, improving model effectiveness by ~20% on average versus prior approaches. Built ETL and ML pipelines for structured and unstructured data, reducing client data preparation effort by 40% and shortening time to first model. Designed NLP text analytics to extract sentiment and patterns from customer feedback and business documents, cutting manual analysis effort by 42%. Deployed models via REST APIs and automated workflows to remove operational bottlenecks in core business processes. Built Tableau and Power BI dashboards used by client leadership to track KPIs and model outcomes. Contributed reusable frameworks and code accelerators that cut model development time by 25% across multiple engagements.