Founding Applied AI Engineer

The role

You will own the applied AI architecture end-to-end, including model selection, RAG, and agentic workflows. You will build Dossbot as a primary interface for operations and engineer AI-assisted tooling for customer schemas and workflows.

What you will do

• Own the applied AI architecture end-to-end including model selection, orchestration, RAG, evals, guardrails, and cost/latency budgets.
• Build Dossbot into the primary interface for operations using natural-language search, analysis, and automation.
• Engineer AI-assisted tooling that uses foundation models to propose, validate, and apply customer schemas and workflow definitions.
• Design agentic workflows that are permission-aware, auditable, tenant-isolated, and safe to run against a customer's system of record.
• Stand up the eval and observability infrastructure to measure quality and detect anomalous behavior.
• Partner with product, design, and the Forward Deployed team to deliver AI use cases.
• Mentor and shape engineering culture as the team's center of gravity for applied AI.

Required qualifications

• Shipped LLM-powered features or agents to production and operated them at scale.
• Deep hands-on work with foundation model APIs, RAG pipelines, tool use/function calling, prompt and context engineering, and fine-tuning.
• Built eval harnesses and guardrails for non-deterministic systems running against business-critical data.
• Strong backend fundamentals in designing systems, Postgres, and cloud services for reliable, multi-tenant web applications.
• Ability to go from 0 to 1 in ambiguous settings.
• Judgment for when AI is the right tool and when it isn't.
• Team player.
• Growth mindset.
• Craftsmanship.
• Customer First.
• Pragmatic.
• Low Ego.

About the company

Doss is building an operations cloud for the real world, an AI-native platform for physical product businesses to manage the flow of goods, dollars, and data. The company recently raised a $55M Series B.