Member of Technical Staff 3

Responsibilities

• Design and build enterprise-grade connectors for varied data sources.
• Implement access-control policies that prevent unauthorized data exposure during search queries.
• Develop CPU-optimized and GPU-based text-classification rules and metadata tagging for sensitive information such as PII, PHI, financial records, and credentials.
• Create unit and integration tests for document extraction, classification, and ingestion pipelines.
• Partner with senior engineers to design, test, and improve enterprise search and retrieval pipelines.
• Architect AI-native data infrastructure and high-performance processing frameworks that convert multi-format enterprise data into AI-ready assets with governance, quality, lineage, and observability.

Requirements

• Recently completed a Bachelor’s or Master’s degree in Computer Science or a related Engineering field.
• 3–6 years of relevant work experience.
• Strong proficiency in Python, Golang, or modern backend engineering technologies.
• Exposure to vector databases, enterprise storage solutions, REST APIs, Retrieval-Augmented Generation architectures, and identity-aware search and retrieval systems.
• Solid foundation in data structures, enterprise-grade security standards, and Git-based version control.
• Familiarity with regex pattern matching, entity-recognition libraries such as spaCy, MedSpaCy, and NLTK, and techniques for validating sensitive data types is preferred.
• Self-motivated, growth-oriented, and eager to be mentored by technical leaders.

Benefits

• Hybrid work arrangement with at least three onsite days per week where the workplace policy applies; specific arrangements vary by location and team.
• Very mild travel requirements.
• Medical, financial, and other benefits, including 401(k) eligibility.
• Paid time off including vacation, sick time, and parental leave.
• Potential eligibility for sign-on bonuses, restricted stock units, and discretionary awards.