AI/ML Engineer - Transforming Healthcare with Scalable ML pipelines

Abhiram Reddy Yarram

AI/ML Engineer 203-***-**** ******************@*****.*** Linkedin

PROFESSIONAL SUMMARY

AI/ML Engineer with 4+ years of experience designing, training, and deploying machine learning, NLP, and deep learning models at scale. Skilled in building end-to-end ML pipelines, developing transformer-based NLP solutions, and implementing model deployments using modern cloud and MLOps tools. Strong background in LLMs, vector databases, and production-grade AI systems across healthcare, insurance, and engineering domains. SKILLS

Programming & Scripting: Python, SQL, Bash, R

Machine Learning & Deep Learning: Scikit-learn, TensorFlow, PyTorch, Keras, XGBoost, Random Forest, CNN, RNN, LSTM, GRU, Attention, Transformers

NLP & LLMs: BERT, T5, GPT models, NLTK, spaCy, HuggingFace, LangChain, Prompt Engineering, Text Classification, NER

Generative AI Tools: RAG, Pinecone, ChromaDB, FAISS, Vector Embeddings, Sentence Transformers

Cloud & MLOps: AWS (EC2, S3, Lambda, ECR), Azure (VMs, AKS, Functions), GCP, GitHub Actions, Docker, DVC

Data Engineering & Big Data: Spark, PySpark, Airflow, ETL Pipelines, PostgreSQL, MongoDB

APIs & Deployment: Flask, FastAPI, REST APIs, Microservices EXPERIENCE

Associate AI Engineer Centene Corporation, Clayton, MO, United States Jan 2025 – Present

Lead the development and deployment of transformer-based models that enhance healthcare outcome predictions by 18%, enabling improved patient risk stratification and care planning.

Architect scalable end-to-end ML pipelines on AWS and Azure, accelerating deployment cycles by 40% and increasing system reliability through automation and containerization.

Leveraged natural language processing (NLP) libraries such as spaCy and NLTK to preprocess and analyze large volumes of textual data for sentiment analysis, entity recognition, and intent classification.

Automate complex data ingestion and preprocessing workflows using Spark and Python, reducing data processing times by 35%, which expedites feature engineering and model training.

Utilized SQL to manage and query relational databases such as MySQL and Pinecone to improve data retrieval efficiency by 40%; enhance model interpretability using attention mechanisms and interactive visualization tools, boosting stakeholder confidence and facilitating data-driven decision-making.

Collaborate with data science, engineering, and product teams to deploy AI models into production, driving wider adoption and delivering measurable business impact. Machine Learning Engineer Insight Global, INDIA Mar 2021 – Jul 2023

Designed and deployed NLP pipelines using BERT and LangChain, which improved text classification accuracy by 20% and enhanced natural language processing capabilities in client applications.

Designed and implemented interactive dashboards using Matplotlib and other visualization tools, leading to a 30% increase in stakeholder engagement.

Developed cloud-integrated RESTful APIs for ML model serving, which decreased latency by 18% and improved real-

time data accessibility for downstream services.

Conducted extensive hyperparameter tuning and model performance evaluation, leading to a 12% increase in predictive accuracy across multiple projects.

Collaborated closely with product owners and engineering teams to align ML developments with business goals, resulting in impactful solutions that enhanced client satisfaction.

Work closely with cross-functional teams to understand business requirements and translate them into AI solutions. Machine Learning Engineer Larsen & Toubro Jun 2019 – Feb 2021

Developed and maintained machine learning models for internal operations and analytics teams, focusing on predicting equipment performance and identifying early patterns of failure.

Designed end-to-end data preprocessing pipelines including cleaning, feature engineering, and dataset preparation for supervised and unsupervised models.

Worked with classical ML algorithms (Random Forest, XGBoost, Logistic Regression) and early deep learning models

(CNN/LSTM) for structured and semi-structured data use cases.

Built small-scale POCs using Python, TensorFlow, and PyTorch to evaluate model feasibility before handing them off to engineering teams for integration.

Supported the deployment of models into internal applications using Flask APIs and basic Docker setups.

Collaborated with cross-functional engineers to understand business challenges and translate requirements into workable ML solutions.

Analyzed model performance, tuned hyperparameters, and tracked improvements using simple experiment logs to ensure reliable outputs in production environments. EDUCATION

Masters In Computer Science - University of Bridgeport, Bridgeport, Connecticut, USA

Contact this candidate