Senior/Principal RAN Digital Twin & AI Simulation Engineer
Parallel Wireless4 months ago
Kefar Sava, IsraelSenior / Staff+
Responsibilities
- Own the technical architecture and roadmap for a multi-RAT RAN digital twin covering LTE, 5G NR, and 2G/GSM.
- Integrate production MAC and scheduler software into deterministic closed-loop simulations and model PHY, channels, UE behavior, traffic, interference, mobility, HARQ, link adaptation, and power control.
- Extend LTE simulation capabilities with reusable abstractions for 5G NR and 2G stacks.
- Design fidelity tiers combining high-fidelity PHY execution with calibrated surrogate and lookup models.
- Develop and evaluate AI/ML-based RAN capabilities including neural channel estimation, learned link adaptation or scheduling, and ML-based PHY or channel surrogates.
- Build datasets, experiment pipelines, algorithmic baselines, reproducible A/B experiments, and KPI-driven evaluations.
- Establish simulation verification and validation practices, including calibration, sim-versus-lab comparisons, divergence analysis, and evidence reporting.
- Build automated unit, component, end-to-end, regression, and performance tests and integrate them into CI/CD workflows.
- Improve simulation speed, scale, observability, and usability for engineering teams.
- Debug discrepancies across C/C++, Python, MATLAB, PHY models, production stack behavior, configurations, and reference measurements.
- Document model assumptions, limitations, calibration provenance, and backend validity.
- Collaborate with RAN stack, PHY, system architecture, AI/ML, automation, and lab-validation teams.
Requirements
- BSc or MSc in Electrical Engineering, Computer Engineering, Computer Science, or a related field, with substantial relevant industry experience; equivalent depth may be accepted.
- Typically 7+ years of hands-on experience in wireless systems, RAN development, modem/PHY development, or system/link-level simulation.
- Deep knowledge of LTE and/or 5G NR L1/L2 behavior, including MAC scheduling, link adaptation, HARQ, CQI/SINR feedback, resource allocation, and uplink power control.
- Strong understanding of digital communications and signal processing, including channel estimation, equalization, coding/modulation, MIMO, propagation and fading models, and performance metrics.
- Experience building or validating link-level, system-level, or hardware-in-the-loop simulations and assessing model validity.
- Strong programming skills in C or C++ and Python, including integration of production native code with simulation and analysis tools.
- Experience with scientific computing and data analysis using NumPy, SciPy, pandas, and visualization frameworks.
- Hands-on experience developing or evaluating machine-learning models for communications, signal processing, time-series data, or related domains using PyTorch, TensorFlow, or an equivalent framework.
- Sound experimental and statistical judgment covering reproducibility, baselines, error analysis, uncertainty, calibration, controlled comparisons, and data-leakage avoidance.
- Experience with Linux development environments, Git, automated testing, containers, and CI/CD.
- Ability to lead technically ambiguous initiatives, make architecture decisions, and communicate across research, product, development, and validation teams.
- PhD in wireless communications, signal processing, or a related area is advantageous.
- Nice-to-have experience includes production eNodeB/gNodeB software, commercial modem stacks, Open RAN products, 3GPP specifications, scheduler algorithms, neural channel estimation, learned receivers, differentiable communications, model compression, ML inference, multi-cell interference, mobility, carrier aggregation, massive MIMO, beam management, GPU acceleration, CUDA, distributed simulation, cloud/HPC execution, SDR, radio test equipment, lab automation, field-log analysis, and internal engineering platforms.
About Parallel Wireless
Parallel Wireless builds open, cloud-native RAN software and solutions for 2G–5G networks used by mobile network operators. Its ALL G O-RAN platform supports interoperable deployments and network automation, with software licensing and services as key revenue streams. Founded in 2012 and headquartered in Nashua, New Hampshire, the privately held company reports engagements with over 50 mobile network operators worldwide.