🚀 We're Hiring: MLOps Engineer
We're looking for an experienced MLOps Engineer to own the deployment, serving, and operational reliability of a self-hosted AI infrastructure running open-weight LLMs, vector databases, and GPU-accelerated inference—all within a secure, on-premise environment.
Key Skills:
✅ Docker & Kubernetes/Docker Compose
✅ vLLM, LLM Serving & GPU Optimization
✅ NVIDIA CUDA & GPU Infrastructure
✅ Python, Linux & FastAPI
✅ Qdrant/pgvector & PostgreSQL
✅ CI/CD, Prometheus & Grafana
✅ RAG Pipelines & Embedding Models
📍 Location: Lahore (On-site)
💰 Salary: PKR 200,000/month