Role Overview :

We are looking for an experienced AI/ML Engineer with strong Telecom Network domain expertise to drive intelligent automation and analytics across network operations. The role focuses on applying AI/ML techniques to OSS platforms (e.g., NetAct), RAN/Core networks, and network data to improve performance, reliability, and operational efficiency.

Key Responsibilities :

1. AI/ML Solution Development for Telecom:

- Design and implement AI/ML models for telecom use cases such as: Network anomaly detection, Fault prediction and root cause analysis, Traffic forecasting and capacity optimization, Predictive maintenance.

- Work with structured and unstructured network data (KPIs, alarms, logs, performance metrics).

2. Telecom Domain Integration (OSS / RAN / Core):

- Work closely with OSS platforms (e.g., NetAct), SON, and network management systems.

- Understand RAN/Core network architecture and integrate AI models into operational workflows.

3. AI-Driven Automation & AIOps:

- Implement AIOps capabilities for: Incident prediction and reduction, Automated alert correlation, Intelligent ticketing and prioritization.

- Enable closed-loop automation using AI insights.

4. Data Engineering & Pipeline Development:

- Build and manage data pipelines for ingesting telecom data from multiple sources.

- Work with big data technologies (e.g., Spark, Kafka, Hadoop).

5. AI Integration in DevOps / CI-CD:

- Integrate AI models into CI/CD pipelines for continuous deployment and monitoring.

- Enable model lifecycle management (MLOps) and work with containerized environments (Docker, Kubernetes).

6. Stakeholder Collaboration:

- Collaborate with network operations, OSS/NetAct engineers, and DevOps teams.

Tech Stack & Requirements:

AI / ML: Python (NumPy, Pandas, Scikit-learn, TensorFlow/PyTorch), time-series analysis, anomaly detection, predictive modeling.

Telecom Domain: RAN / Core / OSS architectures, Network KPIs, NetAct, SON.

Data & Platforms: SQL / NoSQL, Spark, ETL processes.

DevOps / Cloud: Docker, Kubernetes, CI/CD tools (Jenkins, GitLab), MLOps concepts.

Key Success Metrics:

- Reduction in network incidents and MTTR.

- Improved prediction accuracy and model performance.

- Increased automation in network operations.