SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 90,000 - 150,000 / annual
Maxwell is a mortgage technology and fulfillment platform serving hundreds of lending institutions, from independent mortgage banks and credit unions to community banks. The company's flagship Point of Sale product is supported by loan origination, document intelligence, and private-label fulfillment capabilities.
This role is for an applied AI engineer to accelerate Maxwell's document intelligence capabilities and ship the next generation of AI and agentic systems. You will own the design and delivery of production AI and agentic systems across document intelligence, workflow automation, and copilots. Your responsibilities include architecture decisions for LLM-based systems (retrieval, tool use, orchestration, memory, evaluation), building evals and observability for production AI, managing cost and latency at production volume, partnering with product and data engineering teams, providing technical mentorship, and evaluating vendors and models.
You are an applied AI engineer who ships. You have taken LLM-based systems and agentic workflows from prototype to production and understand what that requires: evals, observability, cost management, latency tuning, error handling, and iteration. You have opinions about agent frameworks and architectures built from what you have shipped, but are pragmatic enough to pick the right tool for the job. You work across the stack—designing retrieval systems, wiring up tool calls, building eval harnesses, debugging production outages, and explaining choices to product managers and executives.
Required: 6+ years software engineering experience with at least 2 years shipping production LLM-based or ML systems. Demonstrated experience building and deploying agentic systems with tool use, orchestration, and multi-step workflows. Strong Python proficiency with production-grade code quality, testing, and deployment. Hands-on experience with LLM APIs (Anthropic, OpenAI, AWS Bedrock). Production experience with evals and observability for LLM systems. Experience with retrieval systems, RAG, vector databases, and embedding models. Fluency with cloud infrastructure (AWS preferred), including serverless, containers, and API design. Clear written and verbal communication skills. Ownership mindset.
Nice to have: fintech, mortgage, or regulated industry experience; document AI, OCR, or structured extraction workflows; AWS Bedrock or SageMaker; modern agent frameworks (LangGraph, CrewAI, AutoGen); modern data warehouses and transformation tools; open source AI/ML contributions; production on-call experience.
