About this role
Sr. Staff AI Engineer - On-Prem AI Infrastructure & Agentic Systems at SK hynix memory solutions America Inc.. Location: San Jose, California, United States. Role: designing infrastructure, deploying models, building agents Requirements: 2+ years in AI/ML engineering with on-prem/private-cloud deployment, experience building agentic AI and RAG pipelines, model fine-tuning (LoRA/QLoRA), Python/Linux/Docker/Kubernetes proficiency, and familiarity with vector DBs and AI serving frameworks. Category: Software Development Seniority: Entry Level Tools: vLLM, TGI, Triton, Milvus, Qdrant, FAISS, Kubernetes, Helm, Docker, LangGraph, AutoGen, LoRA, QLoRA, Model Control Protocols (MCP), Python, Linux, Pinecone, Ollama, ONNX, TensorRT, GGUF, BabyAGI, LangSmith, Weights & Biases, Prometheus, Grafana, CI/CD Commitment: Full Time Workplace: Onsite Languages: English