Related skills
aws python go kafka opensearch📋 Description
- Design ingestion pipelines for AWS Bedrock KB and vector stores.
- Build semantic chunking and document processing for retrieval quality.
- Develop vector embedding pipelines with hybrid semantic/keyword search.
- Create real-time telemetry for model monitoring and QA.
- Implement data anonymization and PII detection for privacy.
- Build automated KB refresh and quality monitoring for freshness.
🎯 Requirements
- 5+ yrs software engineering; 4+ yrs ML/AI data pipelines.
- Vector databases: Pinecone, Weaviate, Qdrant, OpenSearch.
- Embedding models: Ada-3, Cohere, BGE, E5.
- Python and Go proficiency.
- MLOps tools: Weights & Biases, MLflow, Kubeflow.
- Strong data pipelines with SQL/NoSQL; AWS data services.
🎁 Benefits
- Experience with AWS Bedrock Knowledge Base or similar managed vector search.
- Hybrid search algorithms for dense and sparse retrieval.
- Reranking models and cross-encoders for retrieval optimization.
- Prompt compression and context window optimization techniques.
- Data governance and lineage tracking tools.
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!