职位描述

About the Role

This opportunity involves working with a partner company to develop data infrastructure that underpins enterprise AI applications, enhancing access to organizational knowledge. The role focuses on creating retrieval systems, maintaining knowledge bases, and designing data pipelines that support generative AI with dependable and precise outputs. It blends responsibilities across data engineering, search technologies, AI enablement, and practical implementation.

The specialist will collaborate closely with architects, engineers, and client teams to build secure, scalable solutions for information retrieval. Core expertise includes retrieval-augmented generation systems, embeddings, vector search methodologies, and governance of enterprise data.

Key Responsibilities

Develop and configure data connectors and ingestion pipelines to integrate authorized enterprise content from platforms such as SharePoint Online, Exchange/Outlook, OneDrive, and Teams into AI-enabled knowledge bases.
Design, maintain, and optimize knowledge base frameworks by leveraging enterprise search technologies, managing indexes, metadata, and content segmentation strategies.
Incorporate structured data repositories including cloud databases, warehouses, and storage systems to aid retrieval and analytical tasks.
Generate and manage vector embeddings, set up vector stores, and fine-tune retrieval systems aimed at AI applications.
Create and refine evaluation methodologies to continually enhance retrieval relevance, accuracy, grounding, and citation standards.
Implement stringent data access controls that adhere to permissions, classification guidelines, privacy mandates, and the principle of least privilege.
Work jointly with architects and engineers to ensure data strategies align with overarching solution architectures and evaluation goals.
Transfer knowledge and best practices to client teams, promoting sustained ownership and operational competency.
Document all aspects of data processing, indexing techniques, retrieval configurations, connector roles, and technical decisions for future reference.
Support ongoing improvement of AI knowledge systems by identifying and addressing data quality challenges and optimization potentials.

Candidate Requirements

Minimum 5 years of professional experience including at least 2 years involving data, search technology, AI retrieval systems, or related fields.
Proven practical experience with search platforms, knowledge base management, retrieval systems, or data pipelines supporting AI functions.
Solid understanding of embeddings, vector databases, retrieval-augmented generation models, and generative AI data workflows.
Expertise in constructing data ingestion processes, connectors, indexing approaches, and content preparation—preferably with enterprise collaboration platforms.
Knowledge of data governance frameworks covering document and user permissions, data classification, privacy safeguards, and protection of sensitive data like PHI/PII.
Familiarity with AWS data and AI services including Amazon Bedrock Knowledge Bases, OpenSearch, Athena, Redshift, RDS, and S3.
Strong analytical capabilities and problem-solving acumen with emphasis on data fidelity, accuracy, and performance.
Ability to work effectively within technical teams and clearly communicate technical concepts to customers and stakeholders.
Preferred experience with enterprise search platforms such as Amazon OpenSearch, Kendra, Amazon Q Business, or similar.
Additional background in data engineering, information retrieval, or AI application development is advantageous.
Experience designing retrieval evaluation frameworks, quality monitoring systems, or working under regulatory compliance is a plus.
Possession of AWS certifications related to data analytics or machine learning would be beneficial.

Benefits and Working Conditions

Competitive contract position with full remote working flexibility.
Engagement in cutting-edge AI, search, and enterprise data projects.
Exposure to modern cloud AI technologies and extensive knowledge management systems.
Collaboration opportunities with skilled architects, engineers, and client teams.
Contribute towards responsible AI adoption by delivering secure and reliable data solutions.
Flexible remote working environment with occasional travel (up to 10%) for workshops and onsite client engagements.
Chance to grow expertise in AWS platforms, retrieval and vector search systems, and generative AI technologies.

Additional Information

This job listing is facilitated by a partner company handling recruitment and next steps independently. Applications are assessed via an AI-powered matching system that ensures objective prioritization based on core role criteria, after which the partner company decides on interviews and assessments. Candidates' data will be processed in compliance with relevant data protection laws including GDPR.

AI tools may aid parts of the hiring process, such as reviewing applications and analyzing resumes, but decision-making remains with human recruiters.

Data / Search Specialist