Hands-on experience building and deploying Graph RAG pipelines, including graph databases and vector stores. Knowledge of DevOps practices, including CI/CD pipelines, infrastructure as code (e.g., Terraform), containerization (Docker), and Git-based workflows for automated build, test, and deployment of ML services. Knowledge of SRE principles, including defining SLIs/SLOs, monitoring and alerting, incident response, root cause analysis, and building for reliability in production systems.
Familiarity with RAG benchmarking and evaluation methodologies (e.g., faithfulness, context recall, LLM-as-judge, golden datasets). Experience fine-tuning LLMs (e.g., LoRA, PEFT) and knowing when to choose fine-tuning over prompting or RAG. Experience building solutions with multi-modal models and agentic workflows (tool use, orchestration, failure handling). Experience designing, building, and deploying AI/ML platforms and services at scale, handling high data volumes and traffic.
LLMOps experience, including production evaluation, guardrails, observability, and cost and latency optimization. Experience building AIOps solutions such as clustering, classification, anomaly detection, and capacity prediction. Familiarity with cloud-native and GPU-backed inference environments (e.g., Kubernetes, model serving). Track record of mentoring engineers, defining reference architectures, and setting best practices for LLM, RAG, and conversational AI.
Experience applying GenAI to content, creative, or marketing workflows. Communication and collaboration skills, with the ability to explain technical concepts to technical and non-technical audiences.