Hiring nowTelecommunications and network intelligence

Radio Network ML Scientist

Also called RAN ML Scientist

A Radio Network ML Scientist models how a radio network behaves and builds optimisation that improves coverage and capacity without breaking service limits. It matters because network quality drives customer experience and operating cost.

What they do

They study how traffic, interference, mobility and configuration interact across cells, using network telemetry to build models of radio behaviour. They turn those models into optimisation methods for resource allocation and parameter settings. They test ideas in simulation first, then design careful trials on live networks with operations teams. They check each change against service constraints such as latency, drops and fairness between users. They write up results in terms operations engineers can act on, and they monitor deployed models for drift, faults and unexpected side effects.

What a strong hire delivers

In the first months, a strong hire delivers a working radio optimisation model tied to a clear target, such as coverage or capacity in a defined set of cells. They also deliver an evaluation that reflects real network context, not just offline accuracy. Expect a trusted simulation or test setup, a documented route into operations systems, and a first measured gain that stays within service constraints.

How you can tell they are good

Ask them to walk through a radio or network optimisation problem they modelled, from telemetry to a deployed change. Strong people explain the radio resource trade-offs plainly and say how they validated results beyond a simulator. They can describe a change that made things worse and how they caught it. Be wary of pure benchmark talk with no operations contact.

Why it is hard to fill

The mix is unusual. Radio knowledge usually sits with telecom engineers, while modelling and optimisation skill sits with data scientists, and few people have credibly done both. Titles vary, and RAN ML Scientist is only one label. Many good candidates are called RAN engineer, optimisation engineer or applied scientist. CVs rarely show whether a model ever reached a live network.

Where to find them

Look at telecom engineers who moved into modelling, and data scientists who spent time in network operations. Typical titles include RAN optimisation engineer, network data scientist, operations research scientist and performance engineer. They come from operators, network equipment makers, telecom software companies and research groups working on wireless systems and network automation.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for a Radio Network ML Scientist

  1. Describe a radio or network optimisation problem you modelled. What data did you use and what changed in the network?

    A strong answer names the telemetry, the objective and the constraints, and ends with a measured network change. Worry if they only describe offline models, cannot say what was deployed, or claim gains without a baseline.

  2. How would you decide whether a coverage gain is real and not a side effect of traffic shifting elsewhere?

    Look for control groups, comparison of neighbouring cells, attention to time of day and load, and checks on service metrics. Worry if they trust a single average or ignore interference between neighbouring cells.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are looking for a Radio Network ML Scientist to model how our radio networks behave and build optimisation that improves coverage and capacity within service constraints. You will work closely with network operations and engineering to take ideas from simulation to live trials.

What you will do

  • Build models of radio network behaviour from network telemetry
  • Develop optimisation methods for radio resource and parameter decisions
  • Design simulation and live trial setups to test changes safely
  • Evaluate models against coverage, capacity and service constraints
  • Work with operations teams to deploy and monitor models
  • Investigate faults, drift and unexpected network effects
  • Document results so engineers can act on them

What you will bring

  • Demonstrated work modelling radio or network performance from real telemetry
  • Experience with time-series modelling on noisy operational data
  • Practical grounding in optimisation or operations research
  • Evidence of taking a model into a live or near-live network setting
  • Understanding of radio resource trade-offs and service constraints
  • Comfort with reliability practices and incident response

Nice to have

  • Experience with distributed data systems
  • Background in network operations or RAN engineering
  • Experience building network simulators

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Time-series modellingAdvancedModel temporal dependencies and forecasts
  • Optimisation and operations researchAdvancedChoose actions subject to objectives and constraints
  • Reliability and incident responseWorkingDetect failures, restore service and prevent recurrence
  • Distributed systemsWorkingDesign reliable work across networked machines

Other roles in telecommunications and network intelligence

Hiring nowTelecom AI EngineerA Telecom AI Engineer builds AI services that help operators diagnose faults and run their networks. Done well, it means faster fault detection…EmergingNetwork Digital Twin SpecialistA Network Digital Twin Specialist builds and maintains a working model of a live network, so teams can test changes and failures safely before they…EmergingAutonomous Network Operations ArchitectAn Autonomous Network Operations Architect designs automation that fixes network faults within set limits and hands anything uncertain to a person…

Related roles in other families

Hiring nowEnergy AI ScientistEnergy, grid and utility intelligenceAn Energy AI Scientist builds models that predict demand, supply or asset condition, so operators and planners can make better decisions when the…Hiring nowGrid AI EngineerEnergy, grid and utility intelligenceA Grid AI Engineer builds AI support into approved grid workflows, so operators get useful forecasts and recommendations without breaking…Hiring nowRenewable Forecasting ScientistEnergy, grid and utility intelligenceA Renewable Forecasting Scientist predicts wind and solar output and says how uncertain each prediction is. Companies use this to plan dispatch…EmergingAI Energy Systems OptimiserEnergy, grid and utility intelligenceAn AI Energy Systems Optimiser tunes how energy assets are run, using models and optimisation within safety and operating limits. They turn…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← Telecommunications and network intelligenceAll new job families

Start a search

Hiring a Radio Network ML Scientist?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.