AI/ML Engineer

About the Company: Our unique 4G/5G vRAN solution is designed to improve quality of experience, enhance spectral efficiency, provide flexibility to the operator in hardware selection, provide full network automation and significantly reduce Total Cost of Ownership (TCO). Our product is designed with leading edge hardware & software technologies. We have a team of passionate professionals who understand mobile network operator's requirements & vision. Our objective is to provide mobile network operators with the equipment required to deploy and expand their 4G/5G networks quickly and efficiently in the most feature rich and cost-effective way. Department Overview: Rakuten Symphony is revolutionizing the telecommunications industry with its innovative Open RAN and cloud-native telecom software solutions. Our mission is to build intelligent, efficient, and highly performant networks globally. The AI/ML team within Rakuten Symphony is a core part of this transformation, specifically focusing on applying advanced machine learning techniques to optimize Radio Access Network (RAN) software performance and functionality. **Join Our Innovative AI Product Team** We are seeking a highly motivated and skilled AI/ML Engineer to join our dynamic and international AI/ML team, with a specific focus on RAN software optimization projects. This is a hands-on role where you will be instrumental in developing, deploying, and maintaining AI/ML models that directly impact the efficiency, capacity, and reliability of next-generation mobile networks. Our team fosters a "missionary" culture, empowering team members to fully own their product responsibilities and develop hybrid skillsets. We value continuous learning, growth, and mutual respect among team members, operating with a flat organizational structure that minimizes hierarchy and fosters a collaborative environment. You will have the unique opportunity to work on solutions that directly enhance the performance of Rakuten Symphony's Open RAN products, contributing to the advancement of mobile network technology on a global scale. Position: AI/ML Engineer - RAN Software Optimization **Why We Hire** To accelerate our efforts in building self-optimizing and intelligent RAN solutions, we are looking for a talented AI/ML Engineer with a strong foundation in machine learning, data engineering, and software development. This role is crucial for integrating AI/ML capabilities directly into our RAN software, enabling automated optimization, predictive maintenance, and enhanced network performance. You will play a key role in developing the next generation of intelligent RAN features. **Position Details** Join our dynamic, international, and agile AI/ML team to design, develop, and deploy advanced machine learning models and solutions specifically for RAN software optimization. You will collaborate closely with RAN engineers, software developers, and product managers to identify optimization opportunities, build predictive models, and integrate AI/ML logic directly into our RAN products. Your focus will be on leveraging AI/ML to improve RAN performance metrics such as throughput, latency, capacity, and energy efficiency. This includes working with diverse datasets from RAN elements, designing robust data pipelines, developing and evaluating ML models, and ensuring their seamless deployment and ongoing monitoring within a production environment. Job Level: Mid-level (at least 3 years of experience) **Objectives** Collaborate with RAN engineering and software development teams to identify and define AI/ML use cases for RAN software optimization. Design and implement robust data pipelines for collecting, processing, and transforming large volumes of RAN-specific data for ML model training and inference. Develop, train, and evaluate machine learning models to address specific RAN optimization challenges (e.g., resource allocation, beamforming, interference management, anomaly detection). Integrate developed ML models and algorithms directly into RAN software components and workflows. Monitor and maintain deployed ML models, ensuring their performance and accuracy in a dynamic network environment. **Responsibilities** Work closely with RAN domain experts to understand network performance issues and identify opportunities for AI/ML-driven optimization. Design, build, and maintain scalable data pipelines for ingesting, cleaning, and transforming various RAN data sources (e.g., KPIs, counters, logs, configuration data). Perform exploratory data analysis to uncover insights and patterns within RAN datasets. Select appropriate machine learning algorithms and frameworks for specific RAN optimization problems. Develop, train, validate, and fine-tune ML models using frameworks like PyTorch or TensorFlow. Implement model inference pipelines and integrate trained models into RAN software components or control loops. Collaborate with MLOps engineers to facilitate the deployment, monitoring, and lifecycle management of ML models in production. Write clean, efficient, and well-documented code in Python and C++ for data processing, model development, and integration. Analyze model performance metrics and network KPIs to assess the impact of AI/ML optimizations. Participate in code reviews, contribute to architectural discussions, and share knowledge within the team. Mandatory Qualifications: **Telecom & Networking Domain Knowledge** Minimum 3 years of professional experience as an AI/ML Engineer, Data Scientist, or Machine Learning Engineer. Familiarity with basic concepts of mobile networks (e.g., 4G/5G, RAN architecture, cellular technologies). Understanding of key RAN performance metrics (e.g., throughput, latency, SINR, RSRP, RSRQ) is a significant plus. Experience working with time-series data and understanding its characteristics in a networking context. **Technical & Fundamental Skills** Bachelor's degree or higher in Computer Science, Machine Learning, AI, Electrical Engineering, Telecommunications, or a related quantitative field. Strong proficiency in **Python** for data manipulation, analysis, and machine learning development. Solid programming skills in **C++** for performance-critical components and integration with existing RAN software. Hands-on experience with at least one major deep learning framework: **PyTorch** or **TensorFlow**. Experience with building and optimizing data pipelines using tools like Apache Spark, Kafka, or similar technologies. Proficiency in SQL for data querying and manipulation. Experience with version control systems (e.g., Git). Familiarity with MLOps principles and tools for model deployment and monitoring (e.g., Docker, Kubernetes, MLflow). Understanding of various machine learning algorithms (e.g., regression, classification, clustering, time-series forecasting, reinforcement learning). Strong problem-solving skills and an analytical mindset. Ability to write clean, maintainable, and efficient code. Tool Sets and Techniques: Programming Languages:** Python, C++ ML Frameworks:** PyTorch, TensorFlow Data Processing:** Pandas, NumPy, Dask, Apache Spark (preferred) Data Storage/Retrieval:** SQL databases, NoSQL databases, Time-series databases (e.g., InfluxDB, Prometheus) Version Control: Git Containerization/Orchestration: Docker, Kubernetes MLOps Tools: MLflow, Kubeflow (preferred) Data Visualization: Matplotlib, Seaborn, Plotly **Language** Fluent English communication skills (both written and spoken) are required as the team operates in English. Rakuten Shugi Principles Our worldwide practices describe specific behaviours that make Rakuten unique and united across the world. We expect Rakuten employees to model these 5 Shugi Principles of Success. Always improve, always advance. Only be satisfied with complete success - Kaizen. Be passionately professional. Take an uncompromising approach to your work and be determined to be the best. Hypothesize - Practice - Validate - Shikumika. Use the Rakuten Cycle to success in unknown territory. Maximize Customer Satisfaction. The greatest satisfaction for workers in a service industry is to see their customers smile. Speed Speed Speed Always be conscious of time. Take charge, set clear goals, and engage your team.