Staff Applied AI Engineer
Agentic Ai
Agentic Workflows
Ai Agent
Ai Agent Platform
Ai Guardrails
Ai Security
Artificial Intelligence
Artificial Intelligence Engineer
Data
Data Analysis
Data Analytics
Data Architecture
Data Integration
Data Processing
Data Science
Database
Databases
Enterprise Ai
Facilities Management
Generative AI
Large Language Models
Llm Observability
Machine Learning
Management
Project Management
Rag Architectures
Security
SQL
Job Description
The Staff Applied AI Engineer role at DOSS is responsible for end-to-end applied AI that powers Dossbot, AI-assisted schema and workflow generation, and agentic automations grounded in live operational data. This position focuses on production architecture, evaluation and safety, and building enterprise workflows that remain tenant-isolated and auditable.
Responsibilities
- Own the applied AI architecture end-to-end, including model selection, orchestration, RAG over the unified operational data model, production evals and guardrails, plus cost and latency budgets.
- Develop Dossbot as the primary operations interface, enabling natural-language search, analysis, and automation grounded in live supply-chain, finance, and ops data.
- Build AI-assisted tooling that uses foundation models to propose, validate, and apply customer schemas and workflow definitions directly on live production tenants.
- Design agentic workflows that operate within enterprise guardrails, including permission-aware execution, auditability, tenant isolation, and safe runs against a customer system of record.
- Stand up evaluation and observability infrastructure to measure quality, detect regressions, and proactively identify anomalous or risky emergent behavior.
- Partner with product, design, and the Forward Deployed team to deliver high-leverage AI use cases.
- Mentor and shape engineering culture as the center of gravity for applied AI, raising standards for how the team builds, evaluates, and ships LLM-powered systems.
Requirements
- Shipped LLM-powered features or agents to production and operated them at scale, with experience beyond prototypes or demos.
- Strong hands-on experience with foundation model APIs, RAG pipelines, tool use and function calling, prompt and context engineering, and fine-tuning when it is warranted.
- Experience building evaluation harnesses and guardrails for non-deterministic systems working with business-critical data.
- Solid backend fundamentals, including system design, Postgres, and cloud services for reliable multi-tenant web applications.
- Ability to go from 0 to 1 in ambiguous settings, with sound judgment on when AI is the right approach and when it is not.
- Collaborative working style, bringing positivity, openness, and curiosity to the team.
- Growth mindset focused on continuous learning and improvement for self, team, and company.
- Craftsmanship and attention to quality in delivered systems.
- Customer-first orientation focused on the customer experience journey and building a product intended to be genuinely delightful.
- Pragmatic decision-making based on the situation, not theory.
- Low-ego collaboration, with effectiveness in environments where team members support one another.
Technologies
- RAG
- Postgres
- Foundation model APIs
- Tool use and function calling
- Fine-tuning
- LLM
Compensation
USD 230,000 - 260,000 per year.
Location
San Francisco, CA (onsite).
Similar Jobs
