• Design and develop backend services and APIs that support AI-powered applications. • Build, experiment with, and improve AI agents and multi-agent workflows. • Integrate Large Language Model (LLM) providers and AI services into production systems. • Contribute to building Retrieval-Augmented Generation (RAG) pipelines using vector databases and retrieval frameworks. • Work on prompt design, prompt optimization, and prompt strategies to improve response quality and reliability. • Help develop evaluation pipelines to measure LLM performance, reliability, and cost. • Collaborate on the architecture of AI platforms and services that support high-scale workloads. • Implement observability and monitoring for AI systems, including tracing, latency, and cost tracking. • Write clean, maintainable, and testable code while contributing to code reviews and engineering best practices. • Support CI/CD workflows and deployment processes for AI-powered services.

• Drive Innovation: Take ownership of AI-centric projects from conceptualization to deployment, helping BenGen stay ahead of the curve. • Build & Experiment: Develop, test, and refine machine learning models and LLM-based applications using the latest frameworks. • Collaborate Across Teams: Work closely with product and engineering leads to integrate AI features into our core offerings. • Optimize & Scale: Analyze model performance and help scale AI solutions to reach our global user base. • Continuous Learning: Stay on top of the rapidly evolving AI landscape, bringing new tools and methodologies to the BenGen toolkit.

• Build AI systems end-to-end: LLM integrations, workflow automation, data pipelines, and custom tooling • Ship production code for client engagements in healthcare, education, and financial services • Work with senior team members to translate business requirements into technical implementations • Iterate on deployed systems based on real-world performance and client feedback • Research and evaluate emerging AI tools against actual client needs • Contribute to internal engineering standards, tooling, and documentation as the firm scales

• Architect and lead end-to-end ML/AI pipelines — including training, fine-tuning, experimentation, and deployment — setting technical standards across the team. • Design and own CI/CD pipelines for ML/AI workflows, including automated testing, model versioning, and continuous delivery to production environments. • Build and maintain scalable ML/AI infrastructure on cloud platforms. • Develop monitoring and observability frameworks to track model performance, data drift, and system health in production. • Develop tools and processes that leverage ML/AI to enhance user experience, extract insights from large datasets, and increase operational efficiency. • Research state-of-the-art ML/AI advancements and translate them into production-ready systems. • Design, build, and maintain APIs for exposing ML/AI models and data services to internal and external consumers. • Mentor junior and mid-level data scientists and engineers, conducting code reviews and driving engineering best practices across the ML organization. • Collaborate with cross-functional stakeholders to scope, prioritize, and deliver high-impact ML/AI solutions. • Perform other duties as assigned.