Specialist - Data Engineering

AI Observability EngineerRole Overview

We are seeking an AI Observability professional to design, implement, and scale production-grade observability for machine learning and large language model applications. The role will focus on model performance, data quality and drift, safety, compliance, cost, latency, reliability, service-level objectives, and user experience.

Key Responsibilities

·Evaluate, integrate, or build observability tools across metrics, logs, traces, and model telemetry.

·Develop telemetry for AI models and endpoints, including latency, token throughput, error rates, and service-level objectives.

·Create self-service dashboards that enable teams to monitor the health, performance, and reliability of AI systems.

·Analyse time-series and operational data to identify trends, anomalies, and areas for improvement.

·Partner closely with machine learning engineers and platform teams to enable trustworthy, production-ready AI systems.

·Design clear and effective visualizations using appropriate graphs, charts, and dashboarding techniques.

Preferred Skills

·Experience with Thanos.

·Working knowledge of Python and Bash scripting.

·Experience working in Agile environments and using Jira.

Required Skills and Experience

At least 5 years of experience creating data visualizations and telemetry dashboards.

·Strong data analysis and visualization skills.

·Hands-on experience with Tableau and Grafana dashboard development.

·Experience with Prometheus, PromQL, and the Thanos monitoring stack.

·Knowledge of SQL, time-series data, and Linux.

·Ability to select and use appropriate visualization formats, including graphs and charts.