Transforming your data into production-ready ML pipelines
I help small to medium businesses build robust machine learning systems, from concept to deployment. Be it a simple data analysis project where you need to gain actionable insights into your data, creating (or maintaining) a database with either structured or unstructured data, buildig a proof-of-concept Machine Learning algorithm or deploy an end-to-end model pipeline in cloud, I can help you. With 5+ years of experience at top companies like Bosch and expertise in MLOps, I deliver scalable solutions that actually work in production.
I specialize in end-to-end machine learning solutions that bridge the gap between research and production
Design and implement scalable machine learning pipelines using PyTorch, TensorFlow, and modern MLOps tools. From data ingestion to model deployment.
Transform raw data into actionable insights using advanced analytics, statistical modeling, and visualization techniques.
Build robust APIs and backend systems using Python, FastAPI, and cloud technologies. Specialized in ML model serving and real-time processing.
Deploy ML models at scale using Docker, Kubernetes, and cloud platforms. Implement CI/CD pipelines for continuous model improvement.
Develop vision systems for autonomous driving, object detection, and industrial applications using state-of-the-art neural networks.
Build intelligent assistants and knowledge systems using Large Language Models, retrieval-augmented generation, and vector databases.
Real-world applications of machine learning across diverse industries
Developing an LLM assistant leveraging Retrieval-Augmented Generation (RAG) framework with OpenWebUI and asynchronous Python libraries to dynamically generate structured project guides tailored to various team roles.
Prototyped integration of various LLMs with proprietary knowledge base to provide natural language query results for enterprise teams, enabling efficient knowledge discovery and retrieval.
Consulted on developing an easily configurable trailer weight detection pipeline using novel neural network architectures and time series analysis for accurate weight estimation.
Implemented a pipeline fusing multi-modal data from multiple cameras, generating point clouds and detecting critical area intrusions for enhanced safety monitoring systems.
Configured label detection pipeline for fine-tuning models to classify various light sources during autonomous driving, improving vehicle perception capabilities.
Designed and trained novel neural network architectures for near-field ultrasound sensor-based object classification system, enabling precise autonomous parking capabilities.
Trained object-based detection system to identify visible faults in cell tower components. Deployed on Jetson embedded devices using model quantization with TensorRT for real-time operation.
Implemented state-of-the-art semantic segmentation and object detection models to classify safe drone landing areas. Deployed on Jetson devices using model distillation for optimal performance.
Proven track record delivering ML solutions for industry leaders
Leading development of data-driven solutions across diversified industries. Recent projects include RAG systems with LLMs, consulting an automobile giant to develop a trailer weight detecton system with time series data, building sensor fusion pipelines for another well-known automotive client, among others.
Developed and maintained visual perception pipelines for autonomous systems. Specialized in novel neural network architectures and embedded deployment on NVIDIA Jetson devices.
Specialized in Machine Learning and Deep Learning. Teaching Assistant for ML courses.
Ready to transform your data into intelligent solutions?
Whether you need a complete ML pipeline, data analysis, or technical consultation, I'm here to help bring your vision to life.