Senior/Principal RAN Digital Twin & AI Simulation Engineer

Parallel Wireless

About The Position

Parallel Wireless is seeking a hands-on wireless systems engineer to lead the development of a multi-RAT digital twin for their Open RAN solution. This digital twin will execute production RAN software, starting with scheduler and MAC behavior, in a closed loop with PHY, channel, UE, traffic, and network models. It will enable engineering teams to design, evaluate, and compare features for LTE, 5G NR, and 2G without requiring a dedicated physical radio setup for every development cycle. This is a senior individual-contributor role at the intersection of wireless systems, simulation, production software, and AI/ML. The successful candidate will evolve an existing LTE end-to-end simulator into a scalable engineering platform for feature development, regression testing, performance optimization, and evidence-based pre-validation. Initial use cases include MAC scheduler and link-adaptation improvements, power control, mobility and interference scenarios, and neural-network-assisted channel estimation. A key aspect of this role is ensuring the digital twin is both fast and trustworthy, defining multiple fidelity levels and establishing repeatable methods for calibrating the twin against lab or field reference data to reduce dependence on continuous lab access while maintaining confidence in simulation results.

Requirements

BSc or MSc in Electrical Engineering, Computer Engineering, Computer Science, or a related field, with substantial relevant industry experience.
Typically, 7+ years of hands-on experience in communication systems, system development, integration, or simulation. Experience with RAN, modem/PHY, or wireless systems is an advantage.
Demonstrated experience building or validating link-level, system-level, or hardware-in-the-loop simulations and explaining where a model is-and is not-valid.
Strong programming skills in C or C++ and Python, including the ability to integrate production native code with simulation and analysis tooling.
Practical experience with scientific computing and data analysis using tools such as NumPy, SciPy, pandas, and visualization frameworks.
Sound experimental and statistical judgment: reproducibility, baselines, error analysis, uncertainty, calibration, controlled comparisons, and avoidance of data leakage or curve fitting.
Experience working in Linux development environments with Git, automated testing, containers, and CI/CD.
Ability to lead a technically ambiguous initiative, make architecture decisions, and communicate clearly across research, product, development, and validation teams.

Nice To Haves

A PhD in wireless communications, signal processing or a related area.
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.
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.
Knowledge of digital communications and signal processing, including areas such as channel estimation, equalization, coding/modulation, MIMO, propagation and fading models.
Extend the current LTE simulation capability and define reusable abstractions that support additional 5G NR and 2G stacks without duplicating the platform.
Experience with MATLAB and Communications/LTE/5G toolboxes or equivalent PHY simulation environments.
Direct experience with production eNodeB/gNodeB software, commercial modem stacks, or Open RAN products.
Knowledge of 3GPP LTE, NR, and/or GERAN specifications and experience translating standards into executable models and test scenarios.
Experience with scheduler algorithms such as proportional fair, round robin, maximum C/I, QoS-aware scheduling, or reinforcement-learning-based resource allocation.

Responsibilities

Own the technical architecture and roadmap for a modular, multi-RAT RAN digital twin covering LTE, 5G NR.
Integrate production MAC and scheduler software into deterministic, per-TTI/slot closed-loop simulations through stable and maintainable interfaces.
Model the interaction among scheduler decisions, PHY processing, propagation channels, UE behavior, traffic, interference, mobility, HARQ, link adaptation, and power control.
Extend the current LTE simulation capability and define reusable abstractions that support additional 5G NR and 2G stacks without duplicating the platform.
Design a fidelity ladder that combines high-fidelity PHY execution with faster calibrated models or lookup/surrogate backends, selecting the least expensive model that is valid for each engineering question.
Develop and evaluate AI/ML-based RAN capabilities, including neural channel estimation, learned link adaptation or scheduling policies, and ML-based PHY or channel surrogates.
Build representative datasets and experiment pipelines; establish conventional algorithmic baselines; measure accuracy, robustness, generalization, latency, and compute cost before recommending integration into production software.
Create reproducible A/B experiments across software builds and algorithm versions, using defined scenarios, seeds, configurations, and KPIs such as throughput, BLER/ACK-NACK behaviour, MCS, resource-block allocation, SINR, transmit power, latency, and fairness.
Establish simulation verification and validation practices: matched sim-vs-lab scenarios, calibration rules, lab-repeatability baselines, divergence analysis, model-version tracking, and evidence reports.
Prevent overfitting the twin to a single setup by separating universal model parameters, setup-specific calibration, and the production algorithms under test.
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 so that stack, PHY, test, and AI engineers can run repeatable experiments independently.
Debug discrepancies across C/C++, Python, MATLAB, PHY models, production stack behaviour, configuration, and reference measurements.
Document model assumptions, limitations, supported operating regions, calibration provenance, and the validity of every simulation or ML backend.
Work closely with RAN stack, PHY, system architecture, AI/ML, automation, and lab-validation teams to convert product questions into measurable simulation campaigns.