
ekemini User
@ekeminiuser1
I build production AI systems for vision, multimodal, and edge applications.
What I'm looking for
At Watershed, I own the real-time video analytics lifecycle, from data collection and model training through deployment, monitoring, and production improvement. I increased video-processing throughput by approximately 33% per GPU and reduced edge inference latency to under 15 ms using ONNX, quantization, and TensorRT.
Previously at Deel, I trained and deployed YOLO and Mask R-CNN models for industrial automation in low-light, heavily occluded environments. I also cut dataset annotation time by approximately 40% with a pre-label-then-review workflow and partnered on REST and gRPC model microservices.
I build across computer vision, NLP, multimodal AI, and MLOps, including vision-language inspection workflows, RAG, MLflow, Docker, AWS, and GCP. I enjoy delivering reliable ML systems end to end and mentoring junior engineers through practical engineering work.
Experience
Work history, roles, and key accomplishments
Machine Learning & Computer Vision Engineer
Watershed
Mar 2023 - Present (3 years 6 months)
Increased real-time video-processing throughput by approximately 33% per GPU and reduced edge-device inference latency to under 15 ms. Integrated vision-language models into inspection workflows and owned the full lifecycle of the real-time video analytics stack.
Trained and deployed object-detection and segmentation models using YOLO variants and Mask R-CNN for industrial automation. Reduced annotation time by approximately 40% through pre-label-then-review workflows and packaged models as REST and gRPC microservices.
Built CNN and RNN models in Python with TensorFlow and PyTorch for forecasting and classification. Created reusable feature-engineering and EDA tooling and containerized model services with Docker for AWS and GCP deployment.
Education
Degrees, certifications, and relevant coursework
University of Uyo
Bachelor of Science, Computer Science
Bachelor of Science in Computer Science from the University of Uyo, completed in 2023.
Tech stack
Software and tools used professionally
Availability
Location
Authorized to work in
Salary expectations
Social media
Job categories
Skills
Interested in hiring ekemini?
You can contact ekemini and 90k+ other talented remote workers on Himalayas.
Message ekeminiGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
