Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
Solvd, IncPosted in November 2026

Senior Data Engineer - Retrieval & RAG Platform

No location providedSenior
Who we'd reach at Solvd, IncFound and reached by Power Apply
Best leadHiring manager

Leads the team this role joins

Team lead

Runs the team day to day

Founder

Decides on early hires

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a senior or staff data engineering role for people with four or more years of software or ML engineering, including at least one retrieval-augmented generation system taken to production and measured with an evaluation suite. It suits engineers who will build the Bedrock knowledge base, the OpenSearch vector collection and the versioned retrieval API for a client, working in pairs with an ingestion engineer. The work is delivered by Solvd, and the posting does not state a location.

What you’ll do

  • Set up a Bedrock knowledge base and an OpenSearch Serverless vector collection in the client's account, using infrastructure code.
  • Implement hybrid retrieval combining vector and keyword search, with metadata filters.
  • Tune top-k values, score thresholds and reranking against a set of test questions.
  • Build a versioned retrieval API on API Gateway and Lambda, with authentication, rate limits, usage metrics and citations.
  • Enforce permission checks at query time so restricted passages are never returned to unauthorised callers.
  • Provide a retrieve-and-generate endpoint for pilot validation.
  • Build a quality dashboard covering relevance, grounding, citation accuracy, freshness, latency and errors.
  • Support a contact centre pilot by capturing retrieval misses and re-running the test suite before changes ship.
  • Write runbooks for model changes, re-embedding and index rebuilds, including cost implications, and hand over to the client's platform team.

What they’re looking for

  • Four or more years as a software or ML engineer, with at least one RAG or enterprise search system in production and measured.
  • Hands-on work with Amazon Bedrock, including Knowledge Bases and retrieve APIs, and with OpenSearch Serverless vector search.
  • Python, with experience shipping Lambda APIs behind API Gateway, including auth, versioning and throttling.
  • Infrastructure-as-code with Terraform or AWS CDK, and CI for deployment into a client account.
  • Practical understanding of chunking, embedding selection, reranking and the trade-offs between relevance, latency and cost.
  • Experience building operational dashboards in CloudWatch or similar tools.

Nice to have

  • AWS Certified Generative AI Developer Professional or AWS Certified Machine Learning Engineer Associate.
  • Experience with RAG evaluation metrics such as faithfulness, context precision and recall, and citation accuracy.
  • Experience integrating with a contact centre Agent Assist product as an API provider.
  • Familiarity with Bedrock Guardrails and permission-aware retrieval over Microsoft 365 content.

What’s on offer

  • Work on AI projects across several industries.
  • A global team with opportunities to collaborate across regions.
  • An inclusive environment focused on learning and responsible AI.

Skills

Questions about this role

How many years of experience are required?

Four or more years as a software or ML engineer, including a RAG or enterprise search system in production.

Which AWS services are used?

Amazon Bedrock Knowledge Bases, OpenSearch Serverless, API Gateway and Lambda.

Is the location stated?

The posting does not state a location or work arrangement.