LlamaIndex Experience with Docker and Kubernetes Fluent written and verbal communication skills in English Working knowledge of some Vector Databases such as OpenSearch, Qdrant, Weaviate, LanceDB, etc. - an advantage Working knowledge with Snowflake, BigQuery, and/or Databricks - an advantage GCP or Azure knowledge (DevOps/MLOps) - an advantage ML More ❯
chatbots. Hands-on use of agent/RAG orchestration frameworks (LangChain, LangGraph, CrewAI, Autogen ). Working knowledge of vector stores (e.g. pgvector, Pinecone, OpenSearch, Weaviate ). Professional English and a product mindset focused on launching, measuring and iterating. Nice to have Fine-tuning or RLHF/DPO on open-source More ❯
San Francisco, California, United States Hybrid / WFH Options
esrhealthcare
using frameworks such as OpenAI GPT or Anthropic Claude. Design and implement RAG pipelines for scalable, real-time applications leveraging vector databases like Pinecone, Weaviate, Opensearch. Develop prompt engineering strategies to optimize model outputs for specific use cases. Design and deploy scalable ML models that integrate with existing systems. End … with LLMs (e.g., OpenAI GPT models, Anthropic Claude) and fine-tuning techniques. Strong understanding of RAG architectures and vector database integration (e.g., Opensearch, Pinecone, Weaviate). API Development: FastAPI, Flask, Django Containerization: Docker, AWS ECS, Kubernetes Cloud & Data Tools: Experience with cloud platforms such as AWS (SageMaker preferred), GCP Vertex More ❯
we use it to power our analytics) OCR engines (we use AWS Textract, GDocAI, and we have used tesseractOCR in the past) Prompt Engineering Weaviate (we use it for RAG in LLM powered tasks and for hybrid searches) Kubernetes (we run Weaviate and other specific services on Kubernetes) CircleCI DataDog More ❯
