
MLOps Engineer (Scalable ML Deployment)
London
Wigi highlights
5+ years, currently operating as Mid-level MLOps Engineer
Built tools that cut AWS SageMaker costs by 30%
Contributed to SageMaker Pipelines for hands-free model retraining
In the current role, contributed to a real-time inference API for ML models using SageMaker endpoints, achieving ultra-low latency (200 ms), high availability and horizontal scalability. During a previous internship, they also developed and deployed simulation models and optimization algorithms for a food supply chain, increasing production rate by a factor of 4.
Other work included developing and deploying in production a multimodal deep learning model to route IT tickets to the correct department and predict failure risks, reducing ticket routing time by a factor of 60 and decreasing the failure rate, while currently processing over 10,000 tickets weekly. Also developed and deployed in production a deep learning time series forecasting model to predict daily fluctuations in banking payments volume, improving forecast accuracy by 60% on average.
Open to offers
Open to new opportunities
Skills
Work experience
Unlocks when they connect with you.
- certifications· 1
- education· 3
Similar available MLOps Engineers
View all- Senior AI Enginer | Applied Machine Learning & Transformers · Coventry, UK · 4 Yrs Exp · Remote · $5,400/mo
- Ai Platform Engineer - Troubleshooting & System Administration · Bucharest, Romania · 4 Yrs Exp · On-site · $2,100/mo
- Computer Vision and MLops Engineer (C++, MySQL) · Lviv, Ukraine · 7 Yrs Exp · Hybrid · $3,300/mo
- ML Infrastructure Engineer (LangGraph, Ansible) · Kharkiv, Ukraine · 10+ Yrs Exp · Hybrid · $4,100/mo
- AI Platform Engineer, AI Infrastructure Architect · Melbourne, Australia · 10+ Yrs Exp · Remote · $5,000/mo