
Sai Chaitanya Pachipulusu
Machine Learning Engineer and Data Analyst
SaiChaitanya
New York
Joined March 2026
Network
3.5K connectionsDRDCGS
KDAGBW
PRCMSM
JMAGBL
STKFSM
MCKF
SBVM
Summary
Practitioner focused machine learning writer who documents implementation details and learnings; maintains a Medium profile with technical posts on model compression and applied ML. medium+1
Hands on ML engineer with end to end project experience, including building and deploying CNN models (example: potato disease classifier) and using MLOps tools like TF Serving and FastAPI. github+1
Hybrid software/ML professional with roles spanning software engineering, ML engineering and data analysis across industry and nonprofit organizations. getclera+1
Active in technical and extracurricular communities: maintains research/academic presence (ResearchGate) and participates in online chess and local events. researchgate+2
I am a hands-on Machine Learning Engineer and Data Scientist who builds and productionizes end-to-end ML systems that turn messy data into reliable, decision-ready products. I design data pipelines and dashboards, optimize model performance for LLM and computer vision workloads, and deploy scalable inference services that improve business outcomes like retention and reporting efficiency. I combine rigorous engineering such as CI/CD, monitoring, and model governance with practical experimentation including A/B testing, cohort analysis, and model compression to deliver measurable impact and reliable production behavior. I am seeking opportunities to lead ML and data products that bridge research and engineering to drive operational improvements. medium+1
Work
Education
Projects
Writing
Quantization, Distillation and Pruning
November 1, 2024Medium article discussing model compression techniques (quantization, pruning, distillation) and their applications to make NLP/LLM models more efficient for deployment.
Potato Disease Deep Learning Project
October 1, 2021Medium article describing an end-to-end CNN-based project for potato disease classification, covering data collection, preprocessing, augmentation, model architecture, training and deployment with TF Serving and FastAPI.