Core infrastructure engineer

Role Overview

We are looking for a skilled Engineer – AIOps Engineering to design, build, and scale the next generation of intelligent operational platforms. This role sits at the intersection of machine learning, LLMs, observability, automation, and service reliability, enabling predictive and autonomous operations across a globally distributed environment.

Responsibilities

• Design and build AIOps models using LLMs or classical ML for anomaly detection, correlation, and root-cause identification.
• Develop operational copilots and chatbots capable of driving automation through natural language.
• Build and maintain feature pipelines using telemetry, logs, metrics, traces, and runtime state.
• Implement predictive operations including capacity forecasting and early warning systems.
• Build knowledge-grounding systems using RAG pipelines, embeddings, and retrieval systems.
• Architect closed-loop automation patterns connecting alerts, insights, and actions.
• Integrate AIOps models with observability platforms and design real-time inference systems for high-volume telemetry.

Requirements

• 3+ years of experience in System Design, Platform & reliability engineering, ML engineering, or AIOps-oriented roles.
• Strong hands-on experience building ML or LLM-based systems using Python, Java, PyTorch, or TensorFlow.
• Experience building automation workflows using tools such as StackStorm, Rundeck, Airflow, or Jenkins.
• Deep understanding of observability data including logs, metrics, and traces using platforms like Datadog, Splunk, Prometheus, Grafana, or ELK.
• Experience designing and deploying RAG pipelines and intent models.
• Strong experience architecting streaming or event-driven systems such as Kafka, Kinesis, or Pub/Sub.
• Familiarity with Kubernetes, microservices, and cloud-native systems.
• Hands-on experience with Claude Code, Codex, or GitHub Copilot.
• Understanding of context engineering, agentic harness frameworks, and experience building MCP servers.

Skills

• Python
• LLMs
• Kubernetes
• Kafka
• RAG Pipelines