Correlation and Causality Engineer
Core
Design and implement correlation, root-cause analysis, and inference solutions using observability data (logs, metrics, traces) to detect anomalies and anticipate incidents for the Avaloq financial technology platform.
Role type
Senior IC Machine Learning Engineer (Observability & Causal Inference)
Builds
Production-grade correlation/inference services, data-driven ML models, and LLM-based applications for incident analysis and troubleshooting.
Domain
Financial Technology (Wealth Management) + Observability + Applied AI
Deliverable
production ML models
Required skills
Java, Python, Machine Learning, Causal Inference, LLMs (RAG, agents, embeddings), Time-series analysis, Anomaly detection, Docker, Kubernetes, CI/CD, Git
Preferred skills
Terraform, Cloud platforms (AWS/Azure/GCP/OCI), Prometheus, OpenTelemetry, Loki, Grafana, vLLM, Hugging Face, PyTorch, TensorFlow
Technologies
Java, Python, LangChain, Ollama, vLLM, Hugging Face, Prometheus, OpenTelemetry, Loki, Grafana, Jenkins, GitLab, Docker, Kubernetes, Terraform, AWS, Azure, OCI, GCP, PyTorch, TensorFlow, pandas, NumPy, scikit-learn
Responsibilities
Design and implement correlation and root-cause analysis solutions linking events, metrics, logs, and traces; Design, train, evaluate, and maintain ML and statistical models for anomaly detection and causal inference; Develop robust, scalable services in Java and Python to productionize models; Design and implement LLM-based applications for incident analysis and knowledge discovery; Select, deploy, fine-tune, and operate AI models on local/on-prem infrastructure; Work with observability stacks to explore data quality and availability; Build and maintain CI/CD pipelines for automated deployment of applications and models.
Seniority
Senior, hands-on IC