Machine Learning Engineer – Deep Learning (Time-Series / Signal Data)
$130,000 - $150,000 + Super
1 day in office/4 from home
The Opportunity:
Want to build production-grade AI that operates on
real-world signal data, not lab experiments?
This role is for an ML Engineer who wants to
own models end-to-end — from raw time-series inputs through to
deployed, high-accuracy event detection in production.
You’ll be working on complex, high-frequency data (think
Wi-Fi, sensor, or similar telemetry) and turning noisy signals into
reliable, real-time classifications using modern deep learning techniques.
This is a
hands-on engineering role, not research-led. You’ll ship models, improve them, and see them used.
What You’ll Be Doing
- Design, train, and deploy deep learning models for time-series and signal classification
- Build models that capture temporal patterns using architectures such as LSTMs, GRUs, and Transformers
- Own the full ML lifecycle — prototyping, evaluation, optimisation, and production deployment
- Define and maintain feature engineering pipelines (windowing, normalisation, signal transformations)
- Set and track model performance benchmarks in real-world environments
- Work closely with data engineers to shape data contracts and ETL pipelines
- Continuously improve model accuracy, latency, and robustness as data scales
What We’re Looking For
- 2+ years of commercial ML experience in applied, production environments
- Strong hands-on experience building deep learning models (not just training notebooks)
- Practical expertise with sequential / time-series models (LSTM, GRU, Transformer-based)
- Proven experience working with time-series, signal, Wi-Fi, sensor, or telemetry data
- Solid Python skills across the ML stack (NumPy, Pandas, scikit-learn, deep learning frameworks)
- Experience taking models from concept to production
- Background in Computer Science, Engineering, Statistics, or a related quantitative discipline