abra is seeking a Senior ML Platform Engineer.

We're looking for a hands-on Senior ML Platform Engineer (MLOps) to build and maintain the infrastructure that powers secure, production-grade AI in an air-gapped environment.

In this role, you'll develop and optimize ML pipelines, model serving, experiment tracking, model registries, vector databases (RAG), dataset versioning, and GPU orchestration. You'll work closely with AI developers, data scientists, and software engineers to deliver scalable, secure, and reliable AI ssolutions

Requirements:

Must have:

• 5+ years of experience in MLOps, ML Platform, DevOps, Infrastructure, or Software Engineering with hands-on experience supporting production ML/AI platforms.
• Strong experience with Kubernetes (or OpenShift/Rancher), Docker/containers, Linux, and production environments.
• Experience with ML lifecycle tools (e.g., MLflow, Kubeflow, Airflow) and model serving frameworks (e.g., vLLM, Triton, KServe).
• Proficiency in scripting (Python/Bash) and experience working closely with ML Engineers and Software Developers.

Nice to have:

• Experience with RAG infrastructure and vector databases (e.g., pgvector, Milvus, Weaviate, Qdrant).
• Experience with CI/CD, Infrastructure as Code (Terraform, Helm, Ansible), and AI gateways or LLM serving platforms.