Senior AI/ML Engineer - Anomaly Detection & MLOps on GCP
Posted Updated
Description
Zinkworks is building a greenfield, data- and AI-driven platform to detect service issues and automate remediation on Google Cloud. You will own the models that detect outages, evolving from anomaly detection to production ML and an eventual LLM-based agent with retrieval and tools.
Join a nine-person squad across data, ML, backend, frontend, UX, QA and platform engineers, delivering in Jira, Git and CI/CD environments. Strong Python and cloud experience are essential.
Own the intelligence at the heart of an AI-driven platform that detects outages and assesses business impact. Develop anomaly detection models and production ML pipelines (MLOps foundations). Serve models in near real time with monitoring and shadow-mode tracking. Train and improve models using production labels and guards for safe autonomous action. Collaborate with data engineering on feature pipelines and with backend on scoring integration. Design an internal AI agent with retrieval, tool use and guardrails. Hands-on experience taking ML models from exploration to production. Strong Python and core data science stack (pandas, NumPy, scikit-learn or similar). Experience with anomaly detection or time-series modelling, including thresholding and noisy labels. Solid understanding of model evaluation, monitoring and drift in a live environment. Experience with MLOps tooling: model registries, experiment tracking, automated retraining and CI/CD for models. Experience on a major cloud platform, ideally Google Cloud (Vertex AI, BigQuery). Ability to explain model behaviour and trade-offs clearly.Skills
Sign in to read and join the discussion.