Role overview

Qualifications

Hands-on experience with search, retrieval, or knowledge-base systems and the data pipelines that feed them.
Working knowledge of embeddings, vector stores, and RAG retrieval patterns.
Experience with data ingestion, connectors, indexing, and content preparation, ideally including Microsoft 365 sources.
Strong understanding of data permissions, document-level / user-level access control, data classification, and governance (including PHI/PII).

Responsibilities

Build and configure connectors and ingestion pipelines bringing approved enterprise content into knowledge bases.
Design and maintain knowledge base structures using Amazon Bedrock Knowledge Bases and Amazon OpenSearch, including chunking, metadata, and indexing strategies.
Integrate structured data sources for retrieval and analysis.
Collaborate with the architect and engineers to align data design with the overall solution and evaluation goals.

Key facts

Remote from: United States
Fixed term
Expert & Leadership (>10 years)
Data Analyst
English

Hard skills

Search Technologies Knowledge Management Amazon Web Services Indexing Database Permissions Context-Based Access Controls Access Controls Data Classification Data Governance Opensearch Amazon MQ Data Engineering Information Retrieval Data Quality

Other skills

Problem Solving

About the company

Numentica LLC

Numentica LLC, founded in 2008, is a team of software experts who have built enterprise software at fortune 500 companies and helped them achieve success. We have worked across industries such as ECommerce, Finance, Marketing and Supply Chain Automation - each of these industries have unique needs, but they share one particular challenge: They need to manage large amounts of structured and unstructured data. Numentica's team specializes in helping companies wrangle big data and making sense of it. We are a niche consulting firm specializing in software product development, business intelligence, and data management. We believe that our success is built on the success of our clients, and we do what it takes to give our clients a sustained competitive edge through value and innovation. By formalizing our experience into innovative tools and frameworks, we help our customers accelerate time-to-market, improve the quality of products and reduce costs. Our unique culture promotes excellence and drives innovation through trust, pride and teamwork. Some key differentiators that help us build enduring relationships with our clients include Mindshare: Our engagement model, partnership mindset and organization structure ensure that our customers get all the mindshare that they need, and more. Team stability: Our staff retention and longevity provides immense confidence to our customers that the investment they make in their teams with us shows excellent ROI. Service orientation: We never forget that we are in the software services business, an attitude that carries tremendous weight in our recruitment process. Our customers get teams that always go the extra mile to advance their businesses. Partnership mindset: As a company, we take a very long-term view to each and every relationship. We invest time and effort that we know is required for the relationship to mature.

Company details

Company typeSME

Company size201 - 500

Links

Website LinkedIn See all jobs

Your match analysis

See how your profile stacks up against this role.

We compared the job requirements to your profile to show where you're strong and where you fall short.

Job description

This is a remote position.

Role Summary

The Data / Search Specialist makes the customer's knowledge usable by generative AI systems. On an embedded enablement pod, the specialist builds the connectors, knowledge bases, and retrieval layers that ground AI applications in approved enterprise content, while
enforcing data classification and access boundaries and transferring these practices to customer staff. The role is hands-on and supports the architect and application engineers throughout delivery.

Key Responsibilities

Build and configure connectors and ingestion pipelines bringing approved enterprise content into knowledge bases, including SharePoint Online, Exchange/Outlook, OneDrive, and Teams.
Design and maintain knowledge base structures using Amazon Bedrock Knowledge Bases and Amazon OpenSearch, including chunking, metadata, and indexing strategies.
Integrate structured data sources such as Amazon Athena, Redshift, RDS, and S3 for retrieval and analysis.
Generate and manage embeddings and configure vector stores for retrieval.
Build a retrieval-evaluation framework and iteratively improve relevance, accuracy, and grounding/citation quality.
Implement document-level and user-level access enforcement so retrieval respects data classification, PHI/PII boundaries, and least-privilege principles.
Collaborate with the architect and engineers to align data design with the overall solution and evaluation goals, and transfer practices to customer staff.
Document data flows, indexing decisions, retrieval configurations, and connector feasibility for handover and reuse.

Required Qualifications

Hands-on experience with search, retrieval, or knowledge-base systems and the data pipelines that feed them.
Working knowledge of embeddings, vector stores, and RAG retrieval patterns.
Experience with data ingestion, connectors, indexing, and content preparation, ideally including Microsoft 365 sources.
Strong understanding of data permissions, document-level / user-level access control, data classification, and governance (including PHI/PII).
Familiarity with AWS data and AI services (e.g., Amazon Bedrock Knowledge Bases, OpenSearch, Athena/Redshift/RDS/S3) and core AWS fundamentals.
Strong problem-solving skills, attention to data quality, and ability to transfer practices to customer staff.

Preferred Qualifications

Experience with Amazon OpenSearch, Kendra, Amazon Q Business, or comparable enterprise search platforms.
Background in data engineering or information retrieval.
Experience building formal retrieval-evaluation methods and quality monitoring.
Exposure to regulated or public-sector environments.
AWS certification in data analytics or machine learning.

Location & Travel

This is a US-only position; candidates must be authorized to work in and based in the United States.
The role is primarily remote but may require travel up to 10% during the engagement for on-site workshops and customer sessions.

Experience Level

5 to 10 years of experience with at least 2 years of relevant technical stack experience.
Should understand AWS fundamentals in addition to the AI/data stack.