Rajaharsha · ML Engineer · 6+ yrs
Mid-LevelAbout Rajaharsha
Rajaharsha is a full-stack machine learning engineer with extensive experience in deploying models to production and leading platform development. He has a comprehensive understanding of the ML process, from academic research to professional settings. His expertise includes optimizing inference for edge devices and developing real-time analytics dashboards. He thrives in high-paced environments, whether collaborating with a team or working independently.
Core expertise
Additional skills(50)
OpenCV
scikit-learn
Pandas
NumpyWhy hire Rajaharsha?
Led early-stage SaaS platform development and deployment on Kubernetes.
Achieved 90% accuracy with occlusion-aware segmentation models.
Reduced latency by 3x by porting deep learning models to ARM architecture.
Generated over 10M data for Indian facial metrics.
Lowered device cost by 60% through innovative machine vision algorithms.
Reduced latency by 3x by successfully porting deep learning models to ARM architecture.
Lowered device cost by up to 60% by developing a machine vision algorithm.
Project highlights(16)
Chatbot for Medical Research Insights – Senior Machine Learning Engineer
Overview: Built an LLM pipeline to streamline the analysis and comprehension of research papers, facilitating easier access to medical research insights. Responsibilities: Handled and processed large text datasets efficiently, implementing pre-processing techniques like tokenization, stemming, and lemmatization. Established task-specific workflows using LLMs, utilizing orchestration frameworks like LangChain and LlamaIndex.
Key outcomes:
Co-authored and published in a Data Science Consortium.
Crystallization Analysis – Senior Machine Learning Engineer
Overview: This solution was designed to save man-hours and reduce lead time in generating results for understanding crystallization processes. Responsibilities: Developed instance segmentation models for monochrome images, applying SSL and N-shot learning for domain adaptation. Utilized AWS Sagemaker and S3FS for robust model training and testing.
Key outcomes:
Achieved 90% accuracy with occlusion-aware segmentation models with minimal annotations.
Segmentation of Individual Meibomian Glands – Senior Machine Learning Engineer
- This solution provides auto assessment of meibomian glands to quantify dry-eye syndrome, automating a crucial diagnostic step.
- Pre-processed datasets to remove noisy annotations and bias with pandas, numpy, and OpenCV.
- Customized segmentation models with pytorch, TIMM, MMSegmentation, and Tensorflow.
- Utilized GCP VertexAI for data management and training.
- Co-authored and published findings in a Data Science Consortium.
Key outcomes:
Co-authored and published in a Data Science Consortium.
Foundation Model Investigation – Senior Machine Learning Engineer
- Deployed all-purpose segmentation models suitable for a variety of datasets, improving model versatility and reusability.
- Investigated Meta's SAM on various datasets for few-shot performance.
- Ported segmentation models to Docker images using FastAPI, Shell, Pytorch, and Tensorflow.
- Deployed models for diverse datasets in JFrog and Kubernetes.
- Integrated image preprocessing methods as APIs with numpy, pandas, OpenCV, and Tensorflow.
Human Gait Analysis – Senior Machine Learning Engineer
- Built a visualization dashboard pipeline for gait analysis, providing real-time insights from sensor data.
- Developed a data processing and storage pipeline using AWS Kinesis and S3 for sensor data.
- Enhanced IMU fusion algorithm using Python for wearable device sensory data.
- Built an MLP framework for data training with CLI, including preprocessing and visualization.
- Established a real-time dashboard in Tableau with anomaly detection algorithms.
6+ years of industry experience
- •Chatbot for Medical Research Insights— Senior Machine Learning EngineerPython · Hugging Face · OpenAI APIs · Langchain +1
- •Crystallization Analysis— Senior Machine Learning EngineerPython · AWS · Kubernetes · OpenCV +1
- •Segmentation of Individual Meibomian Glands— Senior Machine Learning EngineerPandas · Numpy · OpenCV · PyTorch +3
- •Human Gait Analysis— Senior Machine Learning EngineerAWS Kinesis · AWS S3 · Python · Tableau
- •High Contrast Imaging (HCI)— Senior Machine Learning EngineerOpenMMLab · PyTorch · Hugging Face · CellProfiler +1
- •Chatbot for Medical Research Insights— Senior Machine Learning EngineerLangchain · Llamaindex · Streamlit · Milvus +4
- •3D SMPL Fitting and Reconstruction— Machine Learning EngineerPyTorch3D · Numpy · AWS EC2 · Amazon ECS +3
- •Multi Task DeepLearning Model— Research AssistantPython · PyTorch · Celery · TensorFlow
- •Efficient Deep Learning Models for Edge— Software Development Engineer IIKeras · PyTorch · Nvidia Jetson Nano
- •Efficient Multi Object Tracking on Edge— Software Development Engineer IOpenCV · Numpy · Pandas · TensorFlow +8
- •Custom Annotations— Software Development Engineer ISelenium · GCP Vision APIs · Python · AWS S3 +4
- •Ported Deep Learning Models to ARM Architecture— Software Development Engineer IIKeras · Nvidia DeepStream · Apache TVM
- •IoT with AWS Cloud and Jetson Nano— Software Development Engineer IIAWS Kinesis · AWS Lambda · AWS RDS · AWS S3 +1
- •Open Indirect Opthalmascope— Research FellowPython · OpenCV · MATLAB
- •Chatbot for Medical Research Insights— Senior Machine Learning EngineerPython · Hugging Face · OpenAI APIs · Langchain +1
- •Segmentation of Individual Meibomian Glands— Senior Machine Learning EngineerPandas · Numpy · OpenCV · PyTorch +3
- •High Contrast Imaging (HCI)— Senior Machine Learning EngineerOpenMMLab · PyTorch · Hugging Face · CellProfiler +1
- •Chatbot for Medical Research Insights— Senior Machine Learning EngineerLangchain · Llamaindex · Streamlit · Milvus +4
- •Chatbot for Medical Research Insights— Senior Machine Learning EngineerPython · Hugging Face · OpenAI APIs · Langchain +1
- •Chatbot for Medical Research Insights— Senior Machine Learning EngineerLangchain · Llamaindex · Streamlit · Milvus +4
At a Glance
Single contract. Billed in USD.
Typically responds within 4 business hours.
Top Skills
Vetted by WitaristNot sure if this is the right fit?
Tell us your requirements and we'll match you with the best candidates.
Rajaharsha
LLM