Embedded Machine Learning Engineer

Job Description

Embedded Machine Learning and Real-Time Sensor Classification

Please read the following job description thoroughly to ensure you are the right fit for this role before applying.

Introduced by: KO2 Embedded Recruitment Solutions

Client Location: Edinburgh

Salary: £60,000 to £70,000 per annum

The Opportunity

Our client is building the next generation of real-time detection systems that operate at the edge of the network, where connectivity is unreliable and power is constrained. Their vision is straightforward and radical: machine learning models that run on embedded devices, processing sensor data in the field, making instant decisions without relying on cloud infrastructure or continuous data transmission.

This is not a supervised learning problem on tabular business data. This is not model serving from a GPU cluster. This is embedded machine learning in its most demanding form: taking sophisticated sensor-based classification systems and making them run reliably on devices with megabytes of RAM, in real-world environments where data is noisy, conditions are uncontrolled, and failure is not an option.

The client is at the frontier of what embedded ML can do. Most organisations are still building cloud-first systems. They are building ground-truth systems: devices that operate autonomously, make decisions in real time, and remain reliable under the constraints that define actual field deployment.

The Challenge

The engineering challenge is significant. You will be responsible for the complete lifecycle of machine learning models that run on embedded devices. This means:

From Sensor to Deployed Device. You will work with raw sensor data streams from physical devices operating in uncontrolled environments. This data is not clean. It carries noise, calibration drift, temperature sensitivity, and the unpredictable behaviour of systems deployed in the real world. Your job is to transform this stream into a robust, real-time classification model that runs on hardware with severe constraints on memory, computation, and power.

Engineering Under Constraint. Every machine learning decision you make has downstream consequences for embedded systems. A model that requires 512MB of RAM will not run on a device with 128MB. A model that takes 500ms per inference will drain the battery in days. A model that works in the lab but degrades in the field is a failure. You will learn to think like an embedded systems engineer, not a researcher. You will understand that the goal is not maximum accuracy; it is maximum accuracy within the hardware constraints that define your actual platform.

Real-World Iteration. You will take models from lab development through semi-field validation and into live deployment. You will see what happens when your model encounters conditions it has never seen before. You will debug why a model that performed flawlessly during development is behaving unexpectedly in the field. You will iterate based on real-world performance data and build the judgment to know when a model is sufficiently reliable for deployment.

Cross-Domain Transfer. The long-term vision is building a platform where machine learning models and data structures developed for one application can be adapted and transferred to others. You will contribute to demonstrating that this is technically possible; that you can take a model built for one classification task and, with appropriate retraining and adaptation, make it work reliably in a different domain. This is the frontier of applied ML.

The Role

Reporting to the Lead Data Scientist, you will own the development and deployment of machine learning models that sit at the heart of the embedded detection platform. You will work closely with R&D scientists, firmware engineers, hardware designers, and product teams. You will be the bridge between data science and embedded systems. You will own the complete pipeline: from sensor data ingestion and cleaning, through feature engineering and model development, through embedded optimisation and deployment, through field validation and iteration.

Key Responsibilities

• 
  
• Clean, structure, and analyse sensor datasets from real-world deployments for training and evaluation

Develop machine learning models optimised for embedded deployment on resource-constrained devices

Work with TensorFlow Lite, Edge Impulse, or custom firmware deployment strategies to integrate models into actual hardware platforms

Optimise model architecture, quantization, and inference speed to fit hardware constraints without unacceptable loss of accuracy

Collaborate with firmware engineers to integrate your models into live devices, understanding and accommodating their constraints

Test model performance across lab, semi-field, and real-world settings; identify failure modes and iterate

Document training pipelines, feature engineering methods, model validation results, and deployment learnings

Establish reproducible, scalable workflows for model development, retraining, and versioning

Support future platform expansion by demonstrating that models can be adapted across different applications and use cases

Develop model-driven features such as confidence scoring, anomaly detection, and on-device adaptation logic

Must-Haves

• 
  
• 5+ years of applied experience in data science or machine learning engineering roles

Strong, demonstrable experience with machine learning for classification tasks

Proficiency in Python and relevant libraries: scikit-learn, TensorFlow, pandas, NumPy

Real-world experience working with sensor data, time-series data, or IoT data streams

Familiarity with embedded ML tools and approaches: TensorFlow Lite, Edge Impulse, ONNX Runtime, or equivalent

Hands-on mindset; comfortable getting close to hardware, firmware code, and the real-world constraints of device deployment

Clear communication; ability to explain model behaviour, limitations, and engineering trade-offs to non-technical collaborators

Nice-to-Haves

• 
  
• Signal processing experience or background in IoT systems

Previous work deploying models to edge devices or microcontrollers

Experience with model quantization, pruning, or other embedded optimisation techniques

Background in biology, chemistry, environmental science, or related domains

Familiarity with sensor calibration pipelines, metadata tagging, or HDF5

Experience with dataset versioning and ML workflow management: MLflow, DVC, Weights & Biases

Understanding of low-power device design and power budgeting

What Success Looks Like in Year One

Models in the Field, Not the Lab. You will have taken at least one machine learning model from initial development through to embedded deployment on a live device. You will have validated that model across lab conditions, semi-field conditions, and real-world deployment. You will have documented accuracy and reliability benchmarks that the R&D and product teams trust enough to build products around.

A Repeatable ML Pipeline. You will have established clean, documented workflows for model development, feature engineering, validation, and versioning. The process will no longer be ad hoc. When new sensor data arrives, when a new classification task emerges, or when an existing model needs retraining, the team will have a clear, reproducible path forward.

Embedded Constraints Are Second Nature. You will think routinely in terms of memory budgets, latency budgets, and power budgets. You will anticipate firmware engineer constraints before they surface as integration bottlenecks. You will make design decisions that balance model accuracy against hardware reality.

Real-World Reliability Mindset. You will understand that deployment is when learning truly begins. You will have built the infrastructure to monitor deployed models, identify when they degrade, understand why, and iterate. You will have learned the hard lessons about what separates a model that works in the lab from one that works reliably in the field.

Cross-Domain Credibility. You will have contributed technical evidence that machine learning systems can be developed for one application and transferred to others, with appropriate adaptation and retraining. You will understand what transfers and what does not.

Application

Please submit the following:

• 
  
• Your CV

A cover letter (required) explaining your experience with embedded ML and real-world sensor data, and why this particular challenge interests you

Answers to the following questions:

• Can you commit to 3 days per week in Edinburgh?

Describe a time you deployed a machine learning model to an embedded or edge device. What were the hardware constraints, and how did you optimise the model to fit them?

Have you worked with real-world sensor or time-series data? Describe the challenges you encountered and how you addressed them.

What is your current notice period?

Tell us about a time you took a machine learning model or pipeline built for one application and adapted it to a different use case or domain. What was transferable? xwwtmva What had to be rebuilt?

What draws you to embedded machine learning specifically, rather than traditional cloud-based ML or data science