AI in RAN System Developer

Join our Team

At this time, Ericsson Canada Inc. does not provide immigration assistance/sponsorship now or in the future for this position.

About this opportunity 

Artificial Intelligence is rapidly becoming a key enabler for future Radio Access Networks. We are looking for an experienced AI in RAN System Developer who is passionate about applying machine learning and  advanced analytics  to solve real-world telecom challenges. 

In this role, you will contribute from early phase systemization to development of AI-enabled RAN functions that improve network performance, optimize resource utilization and enhance the end-user experience. The focus is on AI for RAN functionality and embedded intelligence, not on building general-purpose Generative AI solutions or Large Language Models. 

You will work with some of the industry’s most advanced Radio Access Network technologies, including latest NR and 5G Advanced capabilities, while contributing to the journey toward 6G and AI-native networks. Working alongside experts in RAN architecture, radio algorithms, system design, software development and research, you will help shape how AI becomes an integral part of future wireless systems. 

This is an opportunity to combine cutting-edge Machine Learning with carrier-grade radio technology, where solutions must be productized and executed efficiently within strict real-time, compute, memory, power and latency constraints. 

What you will do 

• Drive the system design of AI/ML-enabled RAN functions and algorithms, ensuring that machine learning techniques can be productized and executed efficiently within real-time RAN systems. 

• Develop, evaluate and optimize AI-based solutions for use cases such as scheduling, mobility, link adaptation, radio resource management, O&M systems, performance management, network performance analysis and predictive maintenance. 

• Work closely with engineering teams to integrate AI solutions into existing RAN products, software platforms and development flows, from early prototype and proof-of-concept work to production-quality implementation. 

• Evaluate technical and business problems and determine when machine learning provides value compared with classical algorithmic approaches, avoiding indiscriminate use of AI. 

• Design meaningful experiments, data collection strategies and validation methodologies to assess the effectiveness, feasibility and product impact of AI-driven solutions. 

• Analyze data and translate insights into deployable capabilities that can improve network efficiency, latency, throughput, capacity, reliability and user experience. 

• Optimize AI models for deployment under finite CPU, memory, power and latency budgets, balancing AI accuracy against computational cost and operational value. 


• Contribute to the evolution of AI methodologies, lifecycle practices, tooling and best practices for RAN products and future AI-native networks. 

The skills you bring:

Must-have competence 

• Strong Machine Learning fundamentals, including supervised, unsupervised and reinforcement learning, feature engineering and feature selection, model training, validation, performance evaluation, statistical analysis and data-driven decision making. 

• Ability to decide whether a problem should be solved with classical algorithms or Machine Learning, rather than applying AI as a default answer. 

• Experience with resource-constrained systems, including the ability to design models that fit within finite CPU, memory, power and latency budgets. 

• Understanding of inference optimization, model compression, quantization, pruning, acceleration techniques and deployment feasibility on embedded or telecom platforms. 

• Strong software engineering skills, including modern C++, Python for AI experimentation and prototyping, software architecture understanding, CI/CD and the ability to move from prototype to production software. 

• Understanding of telecom and RAN systems, preferably within areas such as scheduling, mobility, link adaptation, RRM algorithms, O&M systems or performance management. 

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, Applied Mathematics, Telecommunications or a related discipline. 

Highly valued competence 

• Experience with AI in real-time systems, including low-latency inference, real-time operating environments and model optimization for production. 

• Experience with hardware acceleration, including FPGA, NPU or GPU deployment. 

• Practical experience with Reinforcement Learning, online learning, policy optimization, decision making under uncertainty and closed-loop optimization systems. 

• Experience with MLOps and AI lifecycle management, including training pipelines, model versioning, dataset management, monitoring, safe deployment and rollback mechanisms. 

• Experience with machine learning frameworks and tools such as TensorFlow, PyTorch or equivalent. 

Behavioral competencies 

• Analytical and data-driven, with the ability to understand complex technical problems and extract actionable insights. 

• Innovative and curious, with a continuous improvement mindset and the ability to explore new solutions and assess their performance in real-life networks. 

• Critical thinker who can assess technical trade-offs and evaluate alternative approaches pragmatically. 

• Collaborative team player who enjoys working across system architecture, software, feature ownership, research and product development boundaries. 

• Intrinsically motivated, with ownership, learning agility and a strong drive to deliver business and customer value.