ML Ops Engineer, Chanakya
Core
Own the model lifecycle for defence and strategic sector deployments, ensuring serving infrastructure, monitoring, evaluation pipelines, and environment management are always on, accurate, and auditable.
Role type
Senior MLOps Engineer (defence/strategic sector)
Builds
Model serving infrastructure, CI/CD pipelines, evaluation harnesses, and operational playbooks for field and lab use
Domain
Defence and strategic sector AI deployments
Deliverable
production ML models
Required skills
Model serving (vLLM, TGI, Triton), quantised model formats (GGUF, AWQ, GPTQ), containerisation (Docker, Kubernetes, K3s, K0s), monitoring/observability (Prometheus, Grafana), Python, CI/CD for ML (GitHub Actions, ArgoCD, DVC), fine-tuning in constrained environments
Preferred skills
Debugging production ML systems under load, building predictive failure systems, writing operational documentation
Technologies
vLLM, TGI, Triton Inference Server, GGUF, AWQ, GPTQ, Docker, Kubernetes, K3s, K0s, Prometheus, Grafana, GitHub Actions, ArgoCD, DVC
Responsibilities
Design and operate model serving infrastructure across on-prem and cloud; Build and maintain CI/CD pipelines for model updates and evaluation-gated deployments; Monitor model performance in production for latency, accuracy drift, and failure modes; Build evaluation infrastructure including A/B testing and model comparison tooling; Manage containerised model serving in constrained, air-gapped, and edge environments; Create runbooks and operational playbooks for Strategic Deployment Engineers; Own incident response for model-layer failures
Seniority
Senior, hands-on IC
