Description

You will design and implement scalable machine learning models for AIOps, focusing on anomaly detection, root cause analysis, and intelligent automation for enterprise systems.

This role is on-site.

Responsibilities

• Develop and optimize advanced anomaly detection algorithms for infrastructure and operational telemetry data.
• Apply causal reasoning frameworks to identify drivers of incidents and operational disruptions.
• Build and deploy time series forecasting models to predict performance degradation and system failures.
• Integrate Generative AI techniques for intelligent summarization, incident triage, and knowledge extraction.
• Mentor junior data scientists and contribute to best practices in MLOps and model governance.

Required Skills

• 6+ years of experience in data science or applied machine learning roles.
• Strong proficiency in Python (NumPy, Pandas, Scikit-learn, PyTorch/TensorFlow).
• Advanced SQL skills for data manipulation and analysis.
• Proven experience with statistical, ML-based, and deep learning-based anomaly detection.
• Practical application of causal inference and causal reasoning methodologies.
• Hands-on experience with large-scale structured and time series datasets.
• Solid knowledge of time series modeling (ARIMA, Prophet, LSTM, state-space models).
• Experience deploying models into production environments.

Preferred Skills

• Experience in AIOps, IT Operations analytics, or observability platforms.
• Exposure to GenAI / LLM-based solutions for operational intelligence.

Key Skills

Education

Not specified