**This role is for someone who can **architect and build** (hands-on) agentic LLM Systems in production, partner deeply with Data Scientists, and obsess over **evaluation, quality, and cost**—while thriving in the ambiguity of zero-to-one product creation.
*** **Build **instruction-based and ML-assisted** classification pipelines for multi-document inputs (themes, narratives, risk taxonomy).
Explore generating data to fine tune small models.
*** **Create **scoring methodologies** (e.g., risk score, severity, momentum/growth, confidence, exposure) with a clear rationale and calibration approach.
*** **Bonus: experience building "risk detection" classifiers and adverse media style pipelines.
****Demonstrated experience building **agentic GenAI architecture** for **commercially successful** product features (not only internal prototypes).
****Strong experience working with **Data Scientists** on ML algorithms, NLP, evaluation design, and productionization.
****Hands-on experience in **AWS and GCP** (Azure acceptable as additional).
**- **Production experience with:** * ****RAG chatbots**** * ****multi-document summarization** (ideally **Graph RAG**)** * ****multi-document classification**** * ****scoring methodologies** (risk scoring is a strong bonus)****Strong **LLMOps** and GenAI product design experience: experimentation ? deployment ? monitoring ? iteration.
*** **Experience in risk/compliance domains (e.g., adverse media, AML, entity investigation workflows).
*** **Knowledge graphs in production (e.g., Neo4j) and graph extraction pipelines.
*** **Experience running annotation programs / building labeled datasets for NLP tasks.
**Powered by a unique ability to gather and streamline data from all corners of an increasingly complex media landscape, our team of journalists and researchers deliver clarity in a world of confusion.
Our mission is to dig deeper into the nuance inherent in social media to establish context, verify the truth and, ultimately, to help our partners make sense of the world.
#J-*****-Ljbffr