Senior Data Engineer, Retrieval & RAG Platform

Solvd, Inc.; United States; Remote; USD 140,000 - 230,000; Full time

Job summary

Solvd, Inc. is a rapidly growing AI-native consulting and technology services firm delivering enterprise transformation across cloud, data, software engineering, and artificial intelligence.

We are seeking a Senior / Staff Data Engineer to own the Bedrock Knowledge Base configuration, OpenSearch Serverless collection, and the retrieval API, with a focus on entitlement-filtered results and scalable operations.

Qualifications

• 4+ years as a software or ML engineer with production RAG or enterprise search experience.
• Hands-on with Amazon Bedrock Knowledge Bases, Retrieve and RetrieveAndGenerate APIs in production.
• Python development shipping Lambda-based APIs behind API Gateway with auth, versioning, and throttling.
• Infrastructure-as-code with Terraform or AWS CDK and CI for client deployments.

Responsibilities

• Stand up Bedrock Knowledge Base and OpenSearch Serverless vector collection from infrastructure code.
• Implement hybrid retrieval with metadata filters and tuning for quality and latency.
• Build retrieval API on API Gateway and Lambda with versioned paths and per-client rate limits.
• Enforce entitlement at query time by filtering on permission metadata.
• Provide Bedrock retrieve-and-generate reference endpoint for pilot validation.
• Build a quality dashboard tracking relevance, grounding, citations, latency, and costs.
• Support contact center pilot weeks 7–9: capture misses, tune, re-run tests.
• Write runbooks for retrieval, embedding updates, and index rebuilds with cost considerations.

Skills

RAG / enterprise search

Python

API design

Terraform / AWS CDK

Cloud dashboards

Tools

Amazon Bedrock

OpenSearch Serverless

Lambda/API Gateway

Terraform

Job description

Solvd, Inc. is a rapidly growing AI-native consulting and technology services firm delivering enterprise transformation across cloud, data, software engineering, and artificial intelligence.

We are seeking a Senior / Staff Data Engineer to own the Bedrock Knowledge Base configuration, OpenSearch Serverless collection, and the retrieval API, with a focus on entitlement-filtered results and scalable operations.