AI Engineer

This job was selected by the SpringCube team to help AI, Data and Cloud Engineers discover relevant San Francisco Bay Area employers. Sign up to view the full employer details and apply directly with the hiring company.

Company Overview

A San Francisco-based vertical AI company is building software that establishes a new state of trust for global commerce and capital markets by automating and streamlining the work of assurance and audit professionals, particularly in cybersecurity, privacy, and financial audits.

The organization develops technology for professionals responsible for enabling trust between businesses. Its platform is trusted by more than 50 of the top 100 accounting and consulting firms for mission-critical work and is backed by leading investment firms and technology investors.

The organization is seeking an AI Engineer to build its intelligence layer, including agentic workflows, AI architectures, and evaluation systems that power enterprise-grade AI agents. This role operates at the intersection of product engineering, applied AI, and production systems.

The successful candidate will design and deploy AI agents that automate complex audit and advisory workflows while ensuring reliability, performance, explainability, and enterprise-grade quality.

Key Responsibilities

Build and Ship AI Agents

• Implement agentic workflows that automate complex audit and advisory tasks.
• Translate customer problems into discrete and testable agent behaviors.
• Integrate LLMs, tools, and retrieval logic into reliable AI agent experiences.
• Monitor and maintain AI agents in production with a focus on reliability and performance.
• Design AI architectures capable of supporting complex enterprise workflows.

Execute with AI-Native Leverage

• Use AI tooling to accelerate the design, development, and testing of software features.
• Rapidly prototype solutions and strengthen them for enterprise-grade reliability.
• Build evaluations and feedback loops to continuously improve agent outputs.
• Develop prompts and retrieval pipelines that perform reliably at scale.
• Apply LLMs, automation, and agent technologies as core engineering tools.

Contribute to Product Impact

• Work closely with senior engineers and product teams to scope and deliver features.
• Translate customer workflows into clear and actionable engineering requirements.
• Identify capability gaps and propose solutions that improve team velocity.
• Collaborate across engineering and product teams to deliver customer-facing AI capabilities.

Required Qualifications

• 1–3 years of experience shipping production software in real-world systems.
• Strong software engineering fundamentals with the ability to build and deploy production applications.
• Proficiency in TypeScript and/or Python.
• Exposure to LLM APIs such as OpenAI, Anthropic, or Gemini, or other AI development tooling.
• Ability to work effectively in ambiguous environments with guidance from senior engineers.
• Strong problem-solving skills and a bias toward building and shipping solutions.
• Excellent communication and collaboration skills.
• Strong attention to detail and commitment to high-quality code and customer-facing experiences.
• Curiosity and the ability to quickly learn new technologies and problem domains.

Preferred Qualifications

• Familiarity with retrieval pipelines, Retrieval-Augmented Generation (RAG), or vector databases.
• Experience with React.
• Experience with PostgreSQL.
• Experience building AI agents or agentic workflows.
• Experience developing evaluation systems or feedback loops for AI applications.
• Understanding of enterprise-grade reliability, security, and explainability requirements.

What Should Excite You

• Enterprise-Grade Reliability: Building systems that professionals depend on for mission-critical work.
• Human-in-the-Loop Design: Determining when AI should automate decisions and when human judgment should remain involved.
• Nuanced Evaluation: Developing feedback structures for complex workflows where judgment and accuracy are essential.
• Explainability: Making AI outputs and reasoning transparent, understandable, and trustworthy.
• Complex Domains: Working within compliance-heavy enterprise environments while maintaining rapid development cycles.
• Shipping Daily Value: Delivering AI agent experiences that customers can use every day.
• AI-Native Engineering: Using LLMs, agents, automation, and modern AI tooling as fundamental parts of the engineering workflow.

Disclaimer

SpringCube curates tech job listings from various company websites to support tech professionals globally.

1.No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.

2.No Client Relationship: This company is not a client of SpringCube unless stated.

3.To Apply: Click the “Apply” button to be redirected to the hiring company’s application page for this job.

4.No Liability: SpringCube is not liable for inaccuracies.**