• Architect and implement GenAI and LLM‑based systems, including fine‑tuning, evaluation, and optimization • Build scalable pipelines for data processing, model training, inference, and continuous improvement • Deploy and manage AI workloads across AWS, Azure, or GCP using cloud‑native services • Integrate embeddings, vector search, and RAG pipelines into production environments • Optimize GPU/accelerator utilization for distributed training and high‑performance inference • Develop automation for CI/CD, MLOps, observability, and model lifecycle management • Ensure cloud security, compliance, and cost‑efficient resource allocation • Evaluate emerging AI frameworks, tools, and cloud services to drive innovation • Partner with cross‑functional teams to translate business needs into technical solutions

• 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