A

AppOmni

Prevents SaaS misconfigurations, over-provisioning, third‑party risks

Staff Software Engineer - AI Automation and Workflows

AI Application Engineering +1Posted on Nov 19
Full-timeRemote in USARemote

About the Job

Requirements

  • The Senior level requires at least 5 years of software engineering experience; the Staff level requires at least 8 years, including setting technical direction across teams.
  • Strong production experience in Python or Go; strength in one language and willingness to work in the other is acceptable.
  • Experience building and operating production data or ETL pipelines, including pulling from external APIs and data lakes.
  • Hands-on experience building production LLM workflows, including prompting, tool calling, structured output, and evaluation.
  • Interest in improving the cost and quality of AI workflows through approaches such as model selection, routing, and caching.
  • Ability to take loosely defined problems, find creative solutions, ship them, and iterate without a detailed specification.
  • Experience with a major cloud provider, ideally Google Cloud, and Kubernetes.
  • Ability to work directly with researchers and internal customers, translate loosely defined workflows into clear requirements, and explain tradeoffs to technical and non-technical audiences.

Responsibilities

  • Build and maintain ETL pipelines that pull data from the company’s SaaS data lake and other internal and external sources, transform it, and deliver it to researchers and agents.
  • Build automation workflows in which large language models triage incoming signals, including vendor change announcements, security feeds, rule health, and customer feedback, and route relevant items to researchers with the reasoning attached.
  • Select suitable models for each workflow step, using smaller or tuned models when sufficient and larger models when beneficial, and improve workflow cost, latency, and accuracy.
  • Build tools that let researchers and agents query and explore data without hand-written queries or engineering tickets.
  • Work with researchers to identify repeatable work and turn it into automated, observable systems.
  • Build evaluation into AI workflows, use researchers’ accept and reject decisions to measure quality and improve prompts, models, and routing, and partner with the data scientist on evaluation methods and customer-feedback learning.
  • Operate the systems built, including monitoring, alerting, and cost tracking, while maintaining tenant isolation, data security, and access controls across pipelines and agent-accessible data surfaces.
  • Build continuous integration, testing, performance, and false-positive tooling for posture and detection rules so researchers can identify regressions before changes ship.
  • At Staff level, set standards for automation and agent workflows across engineering and shape how the data platform supports them.

Desired Qualifications

  • Background in security research tooling, detection engineering, or security analytics.
  • Experience integrating with enterprise SaaS platform APIs, such as Salesforce, Microsoft 365, ServiceNow, Workday, Google Workspace, GitHub, or Atlassian.
  • Experience building MCPs, command-line interfaces, or tools for agent frameworks.
  • Track record designing and operating robust data pipelines using tools such as Apache Airflow, Dataflow, Dataproc, or Pub/Sub.
  • Prior experience with SSPM, CSPM, ITDR, or other posture and identity security products.
  • Experience with LLM observability and evaluation tools such as LangSmith or Arize, or with fine-tuning or distilling smaller models.

About the Company

AppOmni

Prevents SaaS misconfigurations, over-provisioning, third‑party risks

AppOmni provides security for SaaS applications by preventing data exposure caused by misconfigurations, over-provisioning, and risky third-party apps. Its platform continuously scans SaaS configurations (such as ServiceNow and Okta) to detect misconfigurations, enforce protections to block exposure, identify excessive external access, and flag dangerous third-party integrations. It differentiates itself by focusing on end-to-end SaaS data risk across users, identities, and app connections for large enterprises, including many Fortune 100 companies, with a subscription-based model and a free risk assessment for ServiceNow as a lead generator. The goal is to reduce data risk in SaaS environments by preventing misconfigurations, limiting unnecessary access, and controlling third-party connections.

Company size
51-200
Company stage
Series C
Total funding
$123M
Headquarters
San Mateo, CA
Founded
2020

Recently Posted Jobs

Explore more opportunities at AppOmni

See more jobs