About this role
ML Engineer, Edge / On-Device SLM
Location: Lagos
Job Type: Full-time
Responsibilities
- Deploying small language and speech models on Android and other edge devices
- Optimising inference for memory, latency, battery and stability
- Packaging, versioning and rolling out model updates, with rollback
- MLOps pipelines on GCP for testing and releasing edge models
- Integrating the models into a single offline pipeline in the app
- On-device performance logging that reports back when the phone syncs
Requirements
- 3 to 5 years in ML engineering, with hands-on model deployment
- Experience with edge inference frameworks and model optimisation
- Python, plus C++ or another systems language
- Quantisation and performance profiling on constrained hardware
- Model deployment on Android devices
- Bonus: llama.cpp, ONNX Runtime, TFLite or ExecuTorch, on-device speech-to-text or text-to-speech, and low-cost chipsets.
Application Closing Date
Not Specified.