Sr. Network Data Scientist (VOIS)

Job Description:

Run Virtual infrastructure & OSS infrastructure AI & ML activities, in the context of capacity planning w.r.t to provisioned levels, VM dimensioning (w.r.t demand levels) and performance monitoring and troubleshooting for the Vodafone NFV infrastructure.

To analyze the VNF nature based on selected metrics and help with optimal clusterization based on behavioral model.

To support with Data inspection and visualization.

Predictive analysis of certain key parameters. What-If analysis considering different failure scenarios.

Key accountabilities and decision ownership:

• Works independently to solve complex problems and create scalable models/algorithms that will be integrated into VINO OSS tools and products.
• Assess the effectiveness and accuracy of input/output data to improve decision making process and related actions.
• To use analytics to uncover and realize new revenue and cost savings; information management to track and measure key strategic business metrics not available otherwise, and information strategy to identify ways of using information to increase competitive advantage and to improve underlying information architecture for sustained, cost effective delivery of higher quality information.

Core competencies, knowledge, and experience:

• Proven expertise with a variety of Machine Learning techniques like regression & classification (GLM, CART, Ensemble, SVM, Decision Trees, Random Forest), Clustering (K-means), One-Class learning and imbalanced learning with scikit-learn.
• Proven expertise with Deep Learning techniques like ANN, CNN, RNN with LSTMs, GANs using Keras and Tensorflow.
• Proven expertise with Time Series Analysis & Forecasting.
• Hands on proficiency in Python programming, OOP, DS algorithms, File Handling, NumPy, SciPy, Pandas, Flask.
• Top notch problem-solving skills with excellent communication and storytelling skills.
• Ability to work in cross functional teams to translate business issues into potential analytics solutions.
• Knowledge of complete lifecycle of ML products (business understanding - research - model selection based on business and engineering constraints - model scaling and deployment)

Desirable:

• Proven expertise with Deep Reinforcement Learning (Markov decision process and Q-Learning)

Must have technical / professional qualifications:

• Graduate or PG degree in quantitative disciplines like Statistics/ Analytics/ Maths/ Engineering or Operation Research from top ranked universities with exposure to AI/ ML/ Data Mining
• 2-5 years of relevant work experience

#VOIS #BeUnrivalled #Createthefuture