Fullstack Developer
Polysentry
- New York, New York, United States
- New York, New York, United States
À propos
We engage in close collaboration with customers in high-stakes industries, including financial services, legal, and government. The vital insights we deliver play a pivotal role in safeguarding critical assets on a global scale.
Our Company Polysentry is a technology company that provides industry leading data discovery, classification and analysis solutions. Since 2018, Polysentry has been building and deploying mission-ready AI-based platforms that meet rapidly evolving security needs. The company’s software solutions are built for corporate and government organizations.
Our Team Our innovative team is building cutting‑edge Retrieval-Augmented Generation (RAG) systems that significantly improve information retrieval accuracy. We’re working with the latest embedding models, vector databases, and LLMs to develop solutions that maintain critical context during retrieval operations.
The Role We're seeking a Developer to contribute to our advanced RAG platform under the guidance of our senior engineers. You’ll help implement and optimize systems that reduce retrieval failure rates by improving how context is maintained during information retrieval. You’ll get hands‑on experience with contextual embedding techniques while building practical features for our platform.
Responsibilities
Implement document preprocessing pipelines for contextual embeddings and BM25
Build and improve UI components for our RAG system dashboard
Develop integration points between different components of the retrieval system
Test and compare different retrieval strategies across various knowledge domains
Help implement evaluation frameworks to measure retrieval performance
Contribute to documentation and technical resources for both internal and external use
Requirements
Experience with frontend and backend development
Understanding of embedding models and vector search concepts
Familiarity with REST APIs and data processing pipelines
Knowledge of modern web development frameworks
Ability to work with Python for data processing tasks
Experience with databases (SQL and/or vector databases)
Solid testing and debugging skills
Good communication and collaboration abilities
Nice to Have
Experience with BM25, TF‑IDF, or other lexical search algorithms
Knowledge of LLMs and prompt engineering
Familiarity with performance optimization techniques
Understanding of evaluation metrics for information retrieval
Experience with data visualization or dashboard development
Background or interest in NLP or computational linguistics
Previous work with document processing or chunking strategies
We build data integration platforms that enable critical decisions in dynamic, high-risk settings across industrial, commercial, and government operations.
#J-18808-Ljbffr
Compétences linguistiques
- English
Avis aux utilisateurs
Cette offre provient d’une plateforme partenaire de TieTalent. Cliquez sur « Postuler maintenant » pour soumettre votre candidature directement sur leur site.