Correlation and Causality Engineer

A bit about the role

As a Correlation and Causality Engineer you will be part of a team that is responsible for designing and implementing solutions that provide insights, using observability data, to the entire Avaloq. You will combine software engineering and applied AI to turn large volumes of logs, metrics and traces into actionable knowledge: detecting correlations, inferring root causes and anticipating incidents before they impact our clients.

You need to deeply understand how Avaloq works, how the observability stack is operated, how data is collected and how it can be used. This role requires strong technical expertise and hands-on experience in software development and AI, mainly to develop correlation and inference solutions, including data-driven models and LLM-based applications that run on our own infrastructure.

Your key tasks

Correlation, Causality and Inference Solutions

• Design and Implement: build correlation, root-cause analysis and inference solutions that link events, metrics, logs and traces across the Avaloq landscape, turning raw observability data into meaningful insights
• Data-Driven Models: design, train, evaluate and maintain machine learning and statistical models (e.g. anomaly detection, time-series analysis, causal inference) built on observability data
• Productionization: develop robust, scalable and maintainable services in Java and Python, taking models from prototype to production

AI and LLM Solutions

• LLM-Based Applications: design and implement solutions leveraging Large Language Models and related tooling (e.g. RAG, agents, tool/function calling, embeddings, vector stores) to support incident analysis, troubleshooting and knowledge discovery
• Local AI: select, deploy, fine-tune and operate AI models and LLMs on local/on-prem infrastructure, ensuring performance, cost-efficiency, security and data privacy
• Quality and Evaluation: define metrics and processes to evaluate the accuracy, reliability and explainability of AI-based solutions, and continuously improve them

Observability Data and Collaboration

• Data Exploration: work with the observability stack (Prometheus, OpenTelemetry, Loki, Grafana) to understand what data is available, its quality and how it can be best exploited
• Internal Consultancy: interact with teams across the company (DevOps, SRE, application development, product and operations) to understand their needs and identify where correlation, causality and AI can deliver the most value
• Stakeholder Engagement: communicate complex technical insights clearly to stakeholders, enabling informed decision-making and prioritization of new use cases

Engineering Excellence

• Software Engineering Practices: apply high engineering standards, including code reviews, testing, documentation and version control with Git
• CI/CD and Automation: build and maintain CI/CD pipelines (e.g. Jenkins, GitLab/GitHub) for the automated build, test, deployment and monitoring of applications and models
• Operations: deploy and run solutions on containerized platforms, and contribute to the reliability, monitoring and continuous improvement of what you build