Detectare de anomalii Jobs

I have an enterprise decision-analysis product on the roadmap and I need a senior-level Microsoft Azure engineer who is comfortable taking full ownership of the Azure development. The core requirement is an unsupervised machine-learning pipeline—deployed and managed in Azure—that can ingest raw data, uncover patterns autonomously, and feed those insights into the application’s decision engine. Here is what I have in mind: data lands in an Azure Data Lake, is processed through Azure Databricks or Synapse, and the unsupervised models (clustering and anomaly-surfacing techniques are likely candidates) are trained and versioned in Azure Machine Learning. Model output then needs to be exposed via a RESTful endpoint, secured with Azure AD, and consumed by the front-end service...

I am building an intrusion-detection system that relies on entropy-based calculations applied over time windows to flag anomalous behaviour in user activity data. The goal is to detect subtle, previously unseen patterns rather than match against known signatures, so the core of the work is an efficient entropy engine that continuously ingests, time-stamps, and scores each event stream for deviation. My data source will be raw user-activity logs—login records, file interactions, command histories, and similar feeds collected from endpoints and servers. You may assume the logs arrive in near-real time (JSON or CSV) and contain at least a timestamp, user identifier, and event type. The system should: • Parse and normalise each record, maintaining a rolling history per user and fo...

I need a knowledgeable Langfuse user to sit with me on a live screen-share and show, step by step, how to monitor an AI system that is already in production. My main objective is to master Langfuse’s monitoring workflow—specifically performance metrics, error tracking, and user-interaction insights—so I can keep my model healthy and spot anomalies before they affect customers. What I expect during the call • A quick tour of how Langfuse ingests traces and connects to an existing codebase. • Hands-on guidance wiring my app so the right metrics, errors, and interaction events reach the Langfuse dashboard. • A walkthrough of the key dashboards: latency, cost, success-rate views, conversation replay, and any alerting rules I should enable. • Tips ...

I have a steady stream of plain-text machine logs arriving every hour. What I need is a dependable way to sift through each file, detect the anomalous patterns hiding in the noise, and produce a cleaned log (or at least clearly flagged lines) before the next batch rolls in. The raw files are straightforward TXT—no embedded markup or JSON structures—so the solution can focus entirely on pattern analysis rather than parsing exotic formats. Because the anomalies are behavioural rather than simply extreme numeric values, the detection logic must look for irregular sequences, unexpected combinations of fields, or sudden structural deviations. I’m happy with a Python‐based approach (pandas, scikit-learn, PyOD, or similar libraries come to mind), but I’m open to anothe...