15198 - Senior AI/AIOps Engineer

Role: Senior AI/AIOps Engineer

- Starting Date: Immediately
- Contract: CLT at UltraCon's Customer
- Work Location: São Paulo/SP @ Av. Paulista (hybrid: 3x/week - presence in the office is mandatory on Tuesdays, Wednesdays and Thursdays)
- Work Time: Business Hours
- Language: English Advanced

Sobre a posição

We are looking for a Senior AI/AIOps Engineer to build the intelligence layer of an enterprise IT Operations/SRE portal. The role combines production AI/ML, Generative AI, agentic workflows, anomaly detection, observability, and Root Cause Analysis (RCA) capabilities.

The professional will develop production-grade AI solutions, connecting operational data such as metrics, logs, events, and historical incidents to improve anomaly detection, incident analysis, and probable-cause identification.

Key Responsibilities

• Develop production GenAI and agentic AI capabilities.
• Build anomaly-detection and Root Cause Analysis (RCA) systems.
• Connect metrics, logs, events, and historical incidents.
• Evaluate and continuously improve AI assistant and RCA accuracy.

Mandatory Requirements

• Minimum of 7 years of professional experience.
• Experience developing production AI/ML systems used by real users.
• Practical experience with Retrieval-Augmented Generation (RAG), including chunking, embeddings, vector search, hybrid retrieval, and reranking.
• Experience with tool/function calling and structured outputs.
• Experience developing agentic AI solutions using LangGraph, LangChain, Semantic Kernel, or equivalent frameworks.
• Experience implementing restricted tools, guardrails, human approval mechanisms, and auditable actions.
• Experience creating AI evaluation datasets and measuring accuracy and errors to support iterative improvement.
• Experience with time-series anomaly detection, alert deduplication, and noise reduction.
• Strong production Python experience, including automated testing.
• Experience with Pandas, NumPy, and scikit-learn.
• Experience troubleshooting Linux environments.
• Experience troubleshooting Java heap, Garbage Collection (GC), and thread dumps.
• Experience troubleshooting Python services.
• Experience with Splunk SPL, dashboards, and alerts.
• Experience with Prometheus, OpenTelemetry, Dynatrace, or equivalent observability technologies.
• Experience with RCA, AIOps, or incident-analysis systems.
• Experience implementing evidence-based probable-cause ranking.

Preferred Requirements

• Experience with PyTorch or TensorFlow.
• Experience with ServiceNow integrations.
• Knowledge of Java and Spring Boot.
• Experience with Kafka or stream-processing technologies.
• Experience with Docker and CI/CD.
• Experience producing technical documentation.

Languages

• Advanced English — mandatory for professional communication and interviews.

CV Submission Guidelines

Please submit an updated CV in Word format, clearly detailing your hands-on experience with production AI/ML, Generative AI, RAG, agentic AI, anomaly detection, AIOps, RCA, Python, Splunk, and observability technologies. Associate these skills with the companies or projects where they were applied, including the respective periods, your direct responsibilities, the solutions developed, and the results achieved. Where applicable, highlight experience with LangGraph, LangChain, Semantic Kernel, vector search, AI evaluation, Prometheus, OpenTelemetry, Dynatrace, ServiceNow, Java/Spring Boot, Kafka, Docker, and CI/CD.

Further information will be given along the technical interview.