The ideal candidate will be technically sound, disciplined in planning and delivery, confident in engaging with users and handling light project coordination, and receptive to learning and adapting to new tools and technologies.
Feature Implementation: Collaborate with the team to implement features that support mission-critical, 24/7 ad-tech operations with high traffic and low latency.
Model Integration & Optimization: Integrate state-of-the-art LLMs and foundational models via commercial APIs or self-hosted inference setups. Implement strategies to manage model latency, token constraints, context windows, and fallback mechanisms.
Working with application developers and Windows or Linux web administrators to troubleshoot integration, deployment, certificate, metadata, claims, proxy, and environment issues.