Applied AI Engineer

About the Role

We are seeking an Applied AI Engineer to join our team. This role involves working on a variety of tasks including browser agent reliability, document understanding, and inference optimization. The ideal candidate will build systems that improve accuracy and speed of automated processes in finance operations.

Responsibilities

• Work on browser agent reliability, document understanding, and inference optimization
• Build systems that make the work more accurate and faster every week
• Push to state-of-the-art across core automation capabilities such as UI interaction, unstructured data parsing, and tool use
• Design adaptive systems that self-heal when environments change
• Create fine-tuning pipelines that learn from customer-specific workflows
• Optimize latency across the stack through model selection, quantization, caching, and routing strategies

Requirements

• Strong Python and ML frameworks, particularly PyTorch
• Eval-and-metric mindset - focus on metrics that matter in production rather than benchmarks
• Comfort with messy data and figuring out how to make it useful
• Track record of shipping - able to describe specific systems built end-to-end
• Crisp communication about your own work - able to describe what you built in a few clear sentences without buzzwords
• Based in San Francisco or willing to relocate, in-person 5 days a week

Nice-to-Have

• Experience with Reinforcement Learning (RL)
• Experience with Retrieval-Augmented Generation (RAG)
• Experience with Agent-Based Systems
• Experience with Cross-Stack Range: Inference Optimization, Data Pipelines, Fine-Tuning, and Model Monitoring
• Published ML papers or significant OSS contributions
• Laboratory or research exposure (SAIL, BAIR, MIT CSAIL, similar)
• Recent applied work on Large Language Models (LLMs), Browser Agents, Retrieval-Augmented Generation (RAG), or Production AI Workflows