Senior Machine Learning Engineer
HybridLondon, England, United Kingdom
Job Summary
Design, quantize, and deploy edge-native AI models and knowledge analytics engines into air-gapped, degraded, and bandwidth-constrained tactical hardware. Transition state-of-the-art Small Language Models and graph pipelines into low-power runtimes while ensuring full compliance with UK Defence standards for Dependable AI (JSP 936). Build reproducible MLOps pipelines for model training, evaluation, and containerised deployment in restricted environments. Translate complex ML concepts into technical recommendations for MoD stakeholders and Prime contractors. This role supports mission-critical projects securing the UK's digital infrastructure, offering autonomy and rapid iteration within a hybrid working setup.
Required Qualifications
- Active UK SC Clearance (minimum)
- Strong understanding of AI safety, non-repudiation, and human-in-the-loop operational constraints (JSP 936 V1.1 / Dependable AI)
- 3+ years of production experience deploying ML models to edge runtime environments (LiteRT/TFLite, ONNX, C++ bindings)
- Experience in model quantization techniques (INT8, INT4, AWQ) and execution acceleration across NPU/GPU hardware
- Proficiency in Python and PyTorch/HuggingFace ecosystems
- Solid foundation in natural language processing (NLP), semantic summarisation, and graph-based data structures (Graph DBs, vector embeddings, network analysis)
- Understanding of data serialization formats (Protobuf, JSON, XML) and streaming analytics
- Right to work in the UK without sponsorship
- Must have lived in the UK for the last 5+ years continuously
Desired Qualifications
- Experience integrating ML runtimes into Android ART (via Chaquopy, JNI, or native C++ libraries)
- Background in processing military sensor feeds, signals intelligence (SIGRF), or Cursor-on-Target (CoT) data
- Publications or prior project delivery with DSTL, DAIC, or Defence Innovation programs
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.