ML Engineer, CloudlyNet

Cloudly Inc; India; On-site; INR 800,000 - 1,200,000; Full time

Benefits offered by this job

Competitive salary based on experience

Performance-based commission

Festive bonuses

Subsidized meals

Generous holiday leave

Job summary

Cloudly Inc in India is looking for a Machine Learning Engineer to enhance RAN optimization applications. The role involves developing, training, and maintaining crucial machine learning models that impact telecom network performance.

The ideal candidate should have 2-4 years of hands-on experience, strong Python skills, and familiarity with ML frameworks. You’ll work with real datasets to deliver accurate, reliable solutions essential to optimizing network operations.

Qualifications

• 2 to 4 years of experience in ML model deployment.
• Familiarity with MLOps practices.
• Strong communication skills to explain model operations.

Responsibilities

• Design and maintain ML models for RAN optimization.
• Develop Bayesian Digital Twin components.
• Implement data pipelines for UE datasets.

Skills

Python proficiency

Experience with ML frameworks

Bayesian modeling

Time series data handling

Cloud environments (AWS)

Education

Bachelor's or Master's in Computer Science or related

Tools

PyTorch

scikit-learn

Job description

As ML Engineer for CloudlyNet, you will build, train, evaluate, and maintain the machine learning models that power our RAN optimization rApps and the Bayesian Digital Twin at the heart of the platform. You will work with real UE datasets and network topology data to develop models that predict RF behavior, recommend parameter changes, and evaluate the impact of optimization actions before they are applied to live networks. Your work directly reduces OPEX for telecom operators and improves quality of experience for their subscribers. The accuracy, reliability, and explainability of your models matter enormously to customers who operate infrastructure that millions of people depend on every day.

About CloudlyNet

CloudlyNet is a RAN optimization platform that uses a Bayesian Digital Twin with real UE data to reduce energy waste, balance network load, improve mobility, and close coverage gaps for telecom operators and enterprise networks. Its rApps cover Energy Saving, Load Balancing, Mobility Robustness Optimization, and Coverage and Capacity Optimization, all operating through automated SaaS workflows. An AI Copilot layer delivers actionable insights, recommended experiments, and full run history on top of every optimization cycle.

Job Requirements

• Design, train, evaluate, and iterate on ML models for RAN optimization including energy saving, load balancing, mobility robustness, and coverage and capacity optimization
• Build and maintain the Bayesian Digital Twin components that simulate network behavior using UE data and topology baselines
• Develop and improve inference pipelines that power the rApp SaaS workflow: baseline ingestion, training, inference, A/B comparison, and KPI export
• Implement guardrail mechanisms that enforce coverage, fairness, and outage thresholds during optimization runs
• Work closely with the AI Copilot team to surface model outputs, KPI deltas, and recommended actions in explainable, operator-ready formats
• Build and maintain data pipelines for ingesting, validating, and transforming UE datasets and network configuration data
• Monitor model performance in production and implement retraining, drift detection, and model versioning strategies
• Contribute to the multi-tenant model governance framework including tenant isolation, RBAC-aligned model access, and audit trail support
• Engage with the Linux Foundation Maveric open-source project and relevant research to bring the best available approaches into the platform

Desired Experience and Skills

• 2 to 4 years of hands‑on experience building and deploying ML models in production environments
• Strong proficiency in Python and ML frameworks such as PyTorch, scikit‑learn, or equivalent
• Experience with Bayesian modeling, probabilistic inference, or simulation‑based approaches
• Solid understanding of time series data, spatial data, and the challenges of working with real‑world network telemetry
• Familiarity with MLOps practices including experiment tracking, model versioning, and production monitoring
• Comfort working with cloud environments, particularly AWS
• Strong communication skills and the ability to explain model behavior and trade‑offs to non‑ML stakeholders including network engineers and product managers
• Genuine curiosity about telecommunications networks and how ML can make them smarter

Preferred Qualifications

• Experience with RAN optimization, network simulation, or digital twin systems
• Knowledge of 4G/5G network architectures, KPIs, and optimization challenges
• Familiarity with the Linux Foundation Maveric project or open RAN ecosystems
• Experience with reinforcement learning or multi‑objective optimization
• Bachelor's or Master's degree in Computer Science, Electrical Engineering, Machine Learning, or a related field

Compensation & Benefits

• Salary: Competitive base, negotiable based on experience
• Performance‑based commission structure: your earnings scale directly with your results
• Two annual festive bonuses, each equivalent to half a month’s salary
• Two‑day weekends, 10 days casual leave, 10 days sick leave, and 14 public holidays per CloudlyIO’s global holiday calendar
• Fully subsidized lunch and evening snacks, plus tea and coffee throughout the day
• Direct collaboration with US clients and teams, with real exposure to global enterprise AI deals from day one