1 day ago
Buenos Aires, Argentina +2 moreMid Level
Responsibilities
- Design, train, evaluate, deploy, and operate text-classification systems for fraud, spam, abuse, and trust-and-safety detection.
- Curate and label data, run shadow-mode evaluations, and report precision, recall, and calibration by abuse archetype.
- Build detection for adversarial content, including obfuscated brand text, URL and domain evasion, and cross-account template fingerprinting.
- Serve models inline on the messaging send path within strict latency budgets and define fail-open or fail-closed behavior.
- Develop human-in-the-loop fraud review tooling and convert fraud dispositions into replay and training signals.
- Monitor production model drift and collaborate with fraud operations, trust and safety, and engineering teams.
- Participate in code reviews and improve code quality and engineering standards.
Requirements
- At least 3 years of software development and/or machine learning experience.
- Strong proficiency with asynchronous Python web-service frameworks such as FastAPI.
- Production experience building and operating text-classification systems for fraud, spam, abuse, or trust and safety.
- Experience with labeled corpora, holdout sets, precision/recall tradeoffs, and calibration methodology.
- Experience using LLMs as classifiers or judges within a larger decision pipeline.
- Experience deploying and maintaining machine learning models in production.
- Strong communication and cross-functional collaboration skills.
- Preferred experience with A2P messaging abuse, adversarial ML, high-scale data systems, cloud-native infrastructure, or distributed batch scoring.
Tech Stack
Categories
About Telnyx
Telnyx builds a communications platform and AI infrastructure for developers and enterprises, offering SIP trunking, voice and messaging APIs, WhatsApp Business, eSIM/IoT connectivity, and low-latency inference on a private global IP network. The privately held company, founded in 2009 and headquartered in Austin, operates worldwide and holds a Saudi VVSP license with regional anchorsites for data locality. Revenue comes from usage-based APIs and enterprise connectivity services.