Machine Learning Engineer – Model Serving & GPU Ops - Madagascar
JOB DESCRIPTION Machine Learning Engineer – Model Serving & GPU Ops Information Technology |
Ref.: DIA-2026-IT-19 |
■ Location | ■ Seniority | ■ Estimated duration | ■ Contract |
Madagascar – Remote | Intermediate – 2 to 5 years | 4 months to 1 year | To be confirmed |
ABOUT THE PROJECT
Our client, an international multi-entity group, is building a security-critical, privacy-first information system on its own on-premise infrastructure: hardened mobile and desktop applications, hardware-key authentication, legally isolated data for each group entity, and self-hosted finance and AI capabilities.
The programme is delivered by a senior, multi-disciplinary team working in two-week agile sprints, with compartmentalised access and a strong culture of security by design.
WORK ARRANGEMENT
This is a remote position: you will work from home, from Madagascar. No attendance at DI-Africa's offices is required.
THE ROLE
Operate the on-premise inference infrastructure: GPU racking on an air-gapped network, llama.cpp serving, model loading and quantisation, and monitoring that never leaks content.
KEY RESPONSIBILITIES
● Rack and configure GPU servers on an isolated network.
● Deploy and operate llama.cpp inference.
● Load, quantise and update models through the signed import process.
● Implement health metrics that expose no content.
● Prevent any accidental network egress.
TECHNICAL ENVIRONMENT
● Python, Bash, CUDA / driver operations.
● llama.cpp; vLLM and Triton a plus.
● Air-gapped GPU network.
PROFILE
Location | ● Based in Madagascar, working remotely from home. |
Experience | ● Intermediate – 2 to 5 years of relevant professional experience. |
Required skills | ● Inference operations. ● GPU hardware import awareness. ● Strict network egress discipline. |
Nice to have | ● vLLM. ● Triton basics. |
Languages | ● Professional English required; French is a plus. |
Ways of working | ● Work independently on software development tasks. ● Write clean, straightforward, efficient code that meets acceptance criteria and specifications. ● Cover code with unit, property and integration tests where applicable. ● Write code documentation. ● Willingness to handle hardware: YubiKeys, HSMs, air-gapped machines, phone flashing. ● Comfortable working with compartmentalised access. ● Proactive, requiring minimal supervision or mentoring. ● Proactive in identifying potential problems and implementing solutions. ● Efficient time management and respect of deadlines. ● Practical experience with agile software development methods. |
HR Consulting · www.di-africa.com
Confidential – For recruitment purposes only
About DI-Africa
DI-Africa supports industrial, mining, oil & gas and services groups with their hiring across Africa: Employer of Record (EOR), recruitment & sourcing, payroll & compliance, immigration & work permits, international mobility, health insurance.
Our recruitment process
- Online application — acknowledgement within 48 hours.
- DI-Africa interview — conversation with a recruitment consultant.
- Client interview — short-list presented to the client.
- Offer & onboarding — we support you until your first day.