Founding AI Systems Engineer for Real-Time Ops

Doss; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Doss is building an Operations Cloud for real-world product businesses. This role owns applied AI across Doss: Dossbot (query, analyze, automate via chat), AI-assisted schema/workflow generation, and agentic automations that turn back-office work into background processes.

You'll be the technical anchor where foundation models meet a transactional system of record, designing end-to-end AI architectures, guardrails, and scalable infra to support live production tenants.

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/context engineering.
• Built eval harnesses and guardrails for non-deterministic systems.

Responsibilities

• Own the applied AI architecture end-to-end: model selection, orchestration, RAG over the data model, evals, guardrails, and cost/latency budgets in production.
• Build Dossbot into the primary interface for operations: natural-language search, analysis, and automation grounded in live data.
• Engineer AI-assisted tooling that uses foundation models to propose, validate, and apply customer schemas and workflow definitions on live tenants.
• 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 anomalies.
• Partner with product/design/Forward Deployed to deliver high-leverage AI use cases.
• Mentor and shape engineering culture as the team's center of gravity for applied AI.

Skills

LLM-powered features

Foundation models

RAG pipelines

PostgreSQL

Backend systems

Cloud services

Tools

Postgres

Job description

Doss is building an Operations Cloud for real-world product businesses. This role owns applied AI across Doss: Dossbot (query, analyze, automate via chat), AI-assisted schema/workflow generation, and agentic automations that turn back-office work into background processes.

You'll be the technical anchor where foundation models meet a transactional system of record, designing end-to-end AI architectures, guardrails, and scalable infra to support live production tenants.