AI Platform Engineer

Summary Build the scalable infrastructure that powers our AI products — model serving, vector databases, and observability. You make sure agents and models run fast, cheaply, and reliably at scale.

Role Expectations

• Design and operate scalable AI infrastructure: model serving, autoscaling, GPU orchestration, and cost optimization.
• Build and manage vector database infrastructure for RAG and retrieval workloads (indexing, sharding, performance tuning).
• Implement end-to-end observability: metrics, tracing, logging, latency/cost dashboards, and alerting for LLM and agent workloads.
• Build CI/CD and MLOps pipelines for reproducible model and agent deployments with safe rollouts and rollback.
• Ensure reliability, security, and compliance across the AI serving stack.
• Partner with ML and agent engineers to remove infrastructure bottlenecks and improve developer velocity.

Required Skills

• 8+ years in platform, infrastructure, DevOps, or MLOps engineering.
• Strong experience with cloud (AWS/Google Cloud Platform/Azure), containers (Docker), and orchestration (Kubernetes).
• Hands-on with model serving (e.g., vLLM, Triton, TGI, or similar) and inference optimization.
• Experience operating vector databases (Pinecone, Weaviate, pgvector, Milvus, or similar).
• Solid observability and infrastructure-as-code practices; proficiency in Python.

Value adds:

• GPU cluster management and cost/performance optimization at scale.
• Experience working with Healthcare, Life-Science clients.
• Experience supporting production LLM/agent workloads.
• Security and compliance experience for AI systems.