Engineering

Machine Learning Engineer (Production)

Lagos · Nigeria · Hybrid / remote · Full-time

Experience requirements for this role are set in the required qualifications below—some roles ask for more than three years (for example sales leadership). Compensation and benefits are discussed with shortlisted candidates only—we do not publish salary ranges on public postings.

Bridge data science and platform engineering: ship reliable inference, batch pipelines, observability, and release discipline so models stay healthy after launch day.

What you will do

• Design and operate inference services (latency, autoscaling, cold start, cost) aligned with SLOs
• Build and maintain batch and streaming scoring pipelines with idempotency and backfill strategies
• Partner with ML scientists on packaging models, artifacts, and metadata for reproducible deploys
• Instrument services for logging, tracing, and metrics; define alerts tied to business impact
• Drive canary/blue-green or shadow deployments for model updates with rollback plans
• Collaborate on capacity planning, FinOps for GPU/CPU, and incident response for production AI systems
• Document runbooks, on-call expectations, and handover for client or internal operations teams

Required qualifications

• Minimum 3 years of professional software engineering experience, including serving ML or high-scale data systems in production
• Bachelor’s degree in CS, Engineering, or equivalent
• Strong Python; experience with containers (Docker) and orchestration (Kubernetes or managed equivalents)
• Understanding of REST/gRPC APIs, message queues, and at least one major cloud provider’s ML/serving stack
• Hands-on debugging of production issues (latency spikes, memory, dependency failures)
• Familiarity with CI/CD, infrastructure-as-code, and secrets management
• Comfortable reading model artifacts and collaborating on evaluation metrics with data scientists

Preferred qualifications

• Experience with feature stores, model registries, or experiment tracking at scale
• Background in SRE or platform engineering with service-level ownership
• GPU workload optimization or cost profiling experience