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

Hi, I’m Manideep Nagendla, an AI/ML engineer with 5 years of hands-on experience delivering end-to-end machine learning solutions across healthcare and financial services. I focus on building scalable data pipelines, fine-tuning NLP and ML models, and deploying robust AI systems that help teams make faster, more informed decisions. I enjoy enabling trust through explainability and responsible AI, implementing MLOps workflows, and partnering with cross-functional stakeholders to translate complex problems into practical, impact-driven AI solutions that scale in production.…Hi, I’m Manideep Nagendla, an AI/ML engineer with 5 years of hands-on experience delivering end-to-end machine learning solutions across healthcare and financial services. I focus on building scalable data pipelines, fine-tuning NLP and ML models, and deploying robust AI systems that help teams make faster, more informed decisions. I enjoy enabling trust through explainability and responsible AI, implementing MLOps workflows, and partnering with cross-functional stakeholders to translate complex problems into practical, impact-driven AI solutions that scale in production.

Manideep Nagendla

AI Engineer, Data Scientist, Full Stack Developer, +4





Hi, I’m Manideep Nagendla, an AI/ML engineer with 5 years of hands-on experience delivering end-to-end machine learning solutions across healthcare and financial services. I focus on building scalable data pipelines, fine-tuning NLP and ML models, and deploying robust AI systems that help teams make faster, more informed decisions. I enjoy enabling trust through explainability and responsible AI, implementing MLOps workflows, and partnering with cross-functional stakeholders to translate complex problems into practical, impact-driven AI solutions that scale in production.…Hi, I’m Manideep Nagendla, an AI/ML engineer with 5 years of hands-on experience delivering end-to-end machine learning solutions across healthcare and financial services. I focus on building scalable data pipelines, fine-tuning NLP and ML models, and deploying robust AI systems that help teams make faster, more informed decisions. I enjoy enabling trust through explainability and responsible AI, implementing MLOps workflows, and partnering with cross-functional stakeholders to translate complex problems into practical, impact-driven AI solutions that scale in production.

Available to hire

Hi, I’m Manideep Nagendla, an AI/ML engineer with 5 years of hands-on experience delivering end-to-end machine learning solutions across healthcare and financial services. I focus on building scalable data pipelines, fine-tuning NLP and ML models, and deploying robust AI systems that help teams make faster, more informed decisions.

I enjoy enabling trust through explainability and responsible AI, implementing MLOps workflows, and partnering with cross-functional stakeholders to translate complex problems into practical, impact-driven AI solutions that scale in production.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Work Experience

AI/ML Engineer at IBM USA

January 1, 2024 - Present

Led data integration and modeling efforts as AI/ML Engineer. Unified 50TB+ of EHR and claims data by developing PySpark ETL pipelines, reducing data preparation time by 35% and enabling faster access to reliable clinical datasets. Fine-tuned a BERT-based medical NLP model on 500K+ unstructured EHR notes, increasing the number of meaningful features by 40%. Built a disease-risk prediction model in TensorFlow achieving an AUC of 0.91, enabling earlier identification of chronic-condition risks. Integrated SHAP explainability and HIPAA-aligned audit trails to boost clinician trust and drive AI-driven decision making by 20%. Designed an efficient MLOps workflow using Azure DevOps and MLflow to improve model versioning and reduce deployment cycles to 48 hours. Deployed ML models as Docker containers orchestrated with Kubernetes, exposing FHIR-compatible APIs and maintaining sub-200ms inference latency for 10,000+ clinicians. Performed bias analysis and mitigation across demographic groups, r

ML Engineer at Mphasis India

January 1, 2020 - December 1, 2022

Collaborated with bank’s compliance and payment investigation teams to translate analyst workflows into ML requirements for automated classification of SWIFT messages. Cleaned and standardized 8M+ MT103/MT202 payment messages using Python and PySpark, resolving structural variations and improving NLP pipeline inputs. Designed a text-processing workflow for tokenization, field-level normalization, and removal of boilerplate, reducing noise in long instruction fields and improving downstream model clarity. Built a BERT-based classification model using TensorFlow to identify key payment instructions and risk indicators, raising overall model accuracy from 72% to 91%. Managed experiment tracking, model lineage, and reproducibility through MLflow, enabling faster evaluation of iterations. Trained and tuned models on AWS SageMaker, cutting training time by ~20% and enabling more frequent retraining. Packaged the inference service in Docker and deployed on AWS ECS to process 120K+ payment m