Sobre esta vaga de Senior Data Analyst, Network Analytics & AI na Parallelwireless
Parallelwireless · Híbrido · Pune
We are hiring a Senior Data Analyst to turn 5G/LTE network telemetry, crash data and operational metrics into insights that improve network reliability and customer experience.
You' will own analytics from raw data to executive dashboards, and work closely with engineering, product and customer operations.
Required Qualifications
- Bachelor's or Master's in Computer Science, Statistics, Engineering or a related field.
- 10+ years of experience, 5+ years in data analytics, including at least 2 in a senior or lead role.
- Strong SQL and Python (pandas, NumPy); comfortable with large, high-volume datasets.
- Solid grasp of statistics, time-series analysis and anomaly detection.
- Hands-on experience with ML libraries such as scikit-learn, XGBoost or statsmodels.
- Practical knowledge of time-series forecasting (Prophet, ARIMA or similar) and unsupervised anomaly detection (Isolation Forest, clustering).
- Understanding of model evaluation, feature engineering and how to avoid common problems like data leakage and class imbalance.
- Experience with the ELK stack (Elasticsearch, Logstash, Kibana) and Kafka.
- Telecom domain knowledge (RAN, 4G/5G KPIs, O-RAN).
- Familiarity with Kubernetes, cloud platforms (AWS) or data engineering workflows.
- Experience applying LLMs or GenAI (prompting, retrieval-augmented generation, LLM APIs) to analytics or operations use cases.
- Familiarity with deep learning (PyTorch or TensorFlow) for sequence or log data.
- Exposure to MLOps basics: model versioning, monitoring and drift detection.
- Experience with Elasticsearch ML features or AIOps platforms.
Preferred Qualifications
Key Responsibilities
- Analyse large telemetry and event datasets (KPIs, alarms, downtime, crash reports) to find trends, anomalies and root causes.
- Build and validate ML models for anomaly detection, KPI forecasting, crash clustering and root-cause classification on network telemetry.
- Use AI and LLM tools to speed up analysis, such as summarising logs and crash reports, natural-language querying and automated insight generation.
- Work with engineering to move validated models from notebooks into production pipelines and dashboards.
- Define KPIs, metrics and data models with product and engineering teams.
- Write efficient queries and aggregations on Elasticsearch, SQL and Python-based pipelines.
- Leverage AI tools throughout the SDLC — from design and coding to testing, documentation, and troubleshooting — to accelerate delivery while ensuring output is reviewed, validated, and production-ready.
Pronto para se candidatar à Parallelwireless?
Candidatar-se à Parallelwireless
