and implementation. The ideal candidate will have expertise in LLM fine-tuning, prompt engineering, and model migration...
- Generative AI & MLOps: - Hands-on with Vertex AI (Fine-tuning, Prompt Management, Model Registry). - RAG implementation..., embeddings, and relevance evaluation ( >85%). - Advanced Gemini API usage and cost optimization. - LLM evaluation...
Optimization: Achieve latency 85%). - Advanced Gemini API usage and cost optimization. - LLM evaluation frameworks (RAGAS..., LangSmith). - Data Engineering at Scale: - BigQuery ML , Dataflow (Apache Beam), Pub/Sub with 99.9% SLA. - Cloud Native...
documents. Cost Optimization: Achieve latency 85%). Advanced Gemini API usage and cost optimization. LLM evaluation... frameworks (RAGAS, LangSmith). Data Engineering at Scale: BigQuery ML , Dataflow (Apache Beam), Pub/Sub with 99.9% SLA...
documents. Cost Optimization: Achieve latency 85%). Advanced Gemini API usage and cost optimization. LLM evaluation... frameworks (RAGAS, LangSmith). Data Engineering at Scale: BigQuery ML , Dataflow (Apache Beam), Pub/Sub with 99.9% SLA...