About the Role
About Mickai
Mickai® is building SIOS, our Sovereign Intelligence Operating System, designed to give organisations advanced AI capability while keeping their data, infrastructure and intelligence under their own control.
SIOS is already at MVP stage. The core architecture and platform have been built, and we are now working with design partners as we move towards production deployment.
Our technology is designed to operate on customer-controlled infrastructure, including on-premise, offline and air-gapped environments.
Mickai currently has 104 filed UK patent applications containing 2,340 formal claims across technologies including multi-brain orchestration, sovereign memory, offline AI, hardware identity, cryptographic audit and agent safety.
The Role
We are looking for an exceptional Senior AI Specialist & Rust Engineer to join the engineering team as SIOS moves from MVP into production.
You will work closely with our CTO and existing engineering team to harden, optimise and extend an already functioning platform for real-world deployment with our design partners.
This is not a greenfield concept role. The core system exists. The architecture is established. The challenge now is production engineering.
We need someone capable of getting deep into the existing technology, understanding how it works and helping us make it faster, more resilient, more secure and ready to operate at production scale.
This is also not a prompt-engineering role or a position focused on wrapping third-party cloud APIs.
We are looking for a senior engineer who understands AI at a systems level.
What You'll Work On
- Production engineering of the existing SIOS platform
- Developing and optimising production-grade Rust components
- Hardening systems as we progress from MVP to production
- Building and optimising local LLM inference pipelines
- Improving orchestration between specialist AI models and services
- Optimising inference across CPU and GPU infrastructure
- Model quantisation, memory management and hardware-aware inference
- High-performance asynchronous and concurrent systems
- Reliability, observability, recovery and failure handling
- Secure and deterministic execution of AI-generated actions
- Performance profiling and removal of system bottlenecks
- Engineering for on-premise, offline and air-gapped deployments
- Cryptographic signing, auditability and secure execution
- Working across Rust and Python where appropriate
- Supporting technical requirements arising from design-partner deployments
- Taking complex engineering problems through testing, validation and production
What We're Looking For
Strong commercial or production experience with Rust is essential.
We are particularly interested in candidates with experience across several of the following:
- LLMs and modern AI architectures
- Local and on-device inference
- Model optimisation and quantisation
- GPU/CPU inference
- Systems programming
- Async and concurrent Rust
- AI/model orchestration
- Memory and performance optimisation
- Secure software engineering
- Distributed systems
- Python for AI/ML tooling
- On-premise or air-gapped infrastructure
Experience with technologies such as llama.cpp, GGUF, CUDA, ONNX, Hugging Face, Tokio, FFI or comparable technologies would be highly valuable.
Experience with cryptography, hardware-backed security, TPMs, post-quantum cryptography, RAG, multi-agent systems or highly regulated environments would also be advantageous.
You do not need to tick every box. We care about deep technical ability, engineering judgement and evidence that you can solve difficult production problems.
Where We Are
Mickai is not at idea stage. SIOS has reached MVP, the core platform is built, and we are working with design partners as we prepare the technology for production. That creates a very different engineering challenge. We need to take something that works and make it production-ready for organisations where sovereignty,
Requirements
Rust programming
Strong commercial or production experience with Rust is essential.
AI systems knowledge
Understanding AI at a systems level is crucial for this role.
Production engineering
Experience in production engineering to optimize existing platforms is required.
Performance optimization
Ability to improve performance and resilience of systems is necessary.
Nice to Have
Experience with LLMs and modern AI architectures is a plus.
Familiarity with GPU and CPU inference techniques would be advantageous.
Experience in secure software engineering practices is beneficial.
Benefits
Innovative projects
Work on cutting-edge technology with significant impact.
Collaborative environment
Join a team that values collaboration and technical excellence.