Pepper Auditors Logo

Pepper Auditors

Principal Software Engineer, AI

Posted 21 Days Ago
In-Office or Remote
Hiring Remotely in United States
180K-230K Annually
Expert/Leader
In-Office or Remote
Hiring Remotely in United States
180K-230K Annually
Expert/Leader
Build and scale an AI-powered audit workbench that transforms raw evidence into reviewable workpapers. Responsibilities include designing ingestion and extraction pipelines, deterministic recomputation and exception detection, workpaper generation, evaluation infrastructure, and frontend review tools. The role emphasizes production LLM reliability, golden-dataset evaluations, schema design, traceability, deterministic regulatory logic, structured human review, and end-to-end system ownership in a regulated domain.
The summary above was generated by AI

About Pepper Auditors

Pepper's mission is to protect the integrity of every American's employee benefit plan. We are a fast-growing team of technologists and CPAs working to build a modern audit firm that can serve as the fulfillment engine for federally mandated compliance work streams.

The Role

We’re looking for an experienced software engineer to help build and scale our audit workbench; a pipeline-based harness — not a generic agent loop — that takes an engagement from raw evidence to reviewable workpaper. As of today that looks roughly like:

  • Ingestion and extraction

  • Recomputation and exception detection

  • Workpaper generation

  • Eval infrastrcuture

  • Frontend review surface

As one of the first engineering hires, you will help set the technical direction to ensure our audit wokrbench is usable and scalable from our our first 100 clients to our next 10,000.

The hard part

Most "build an AI agent" roles optimize for demo velocity. This one optimizes for a number a CPA stakes their license on. The reliability of this system comes from schema design, deterministic rule logic, validation, and structured human review — not from hoping the model is good. You'll spend as much time on the deterministic-versus-stochastic boundary, eval harnesses, and traceability as on prompts and orchestration. The model does extraction and narrative drafting; the math and the regulatory logic are exact code. If "build something auditable, reproducible, and provably correct in a regulated domain" is more interesting to you than "ship a chatbot," you'll like it here.

You're a strong fit if you

  • Have shipped production LLM systems where correctness mattered — extraction pipelines, agentic workflows, or document-understanding systems — ideally in a domain with real consequences (fintech, legal, healthcare, regtech).

  • Build evals as a reflex. You've maintained golden datasets and caught regressions before they reached users, and you treat "we can't measure whether this got better" as an unacceptable state.

  • Have strong judgment about where to use a model and where to write a deterministic function — with a hard bias toward the latter when dollars or compliance are on the line.

  • Are a genuine 0→1 builder — you can own a system end-to-end, ship it, and operate it in production. You're energized, not unsettled, by being the second engineer in the building.

  • Treat engineering hygiene as default, not overhead.


Nice to haves

  • Familiarity with accounting, audit, ERISA, 401(k) administration, or financial document processing. You do not need audit experience. Our partner CPAs own the domain end-to-end, and the regulatory logic lives in versioned, deterministic code you'll help build.

  • Layout-aware / OCR extraction, retrieval systems, or structured-output generation.

  • Experience building internal tools or review-and-approval UIs.

Logistics

  • Compensation: Estimated $180,000–$230,000 base + equity

  • Location: Remote-first (U.S.).¹ Columbus, Ohio is a plus but not required.

  • Reporting: Directly to the founding team, partnering closely with our partner CPAs on domain and review standards.

We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.

Similar Jobs

2 Days Ago
Remote or Hybrid
239K-366K Annually
Expert/Leader
239K-366K Annually
Expert/Leader
Automotive • Big Data • Information Technology • Robotics • Software • Transportation • Manufacturing
Principal Software Engineer leading architecture and technical strategy for an in-vehicle AI assistant platform. The role spans Android Automotive client applications, cloud services, edge-cloud orchestration, conversational AI, gRPC, streaming interfaces, testing, telemetry, and distributed systems. Responsibilities include cross-functional architectural alignment, roadmap development, resolving complex reliability and privacy trade-offs, integrating AI frameworks, and mentoring senior engineering teams.
Top Skills: AndroidAndroid Automotive OsArtificial IntelligenceCloud ComputingDistributed SystemsEdge-Cloud ComputingGrpcJavaKotlinLarge Language ModelsMachine LearningMicroservicesRestStreaming Apis
16 Days Ago
In-Office or Remote
150K-242K Annually
Senior level
150K-242K Annually
Senior level
Aerospace • Artificial Intelligence • Computer Vision • Software • Analytics • Defense • Big Data Analytics
Design, develop, and deploy AI-native software products that transform large-scale geospatial data into actionable intelligence. Build multi-agent workflows using orchestration frameworks and large language models, engineer tool-using and self-refining agents, develop data ingestion pipelines, and operate secure, scalable AI systems in production. Apply DevOps, reinforcement feedback mechanisms, and AI-assisted development practices while contributing to engineering standards and documentation.
Top Skills: AWSCi/CdClaudeClaude CodeCodexDistributed SystemsDockerEmbeddingsGeminiGemini CliGoogle AdkGoogle Cloud PlatformGpt-4JavaScriptKubernetesLangchainLanggraphPythonRetrieval-Augmented GenerationVector Databases
2 Days Ago
Remote
USA
250K-300K Annually
Expert/Leader
250K-300K Annually
Expert/Leader
Fintech • Payments • Financial Services
Own end-to-end AI and platform initiatives, designing scalable applications, agentic workflows, and reusable AI capabilities for loan origination and servicing. Build and operate production LLM systems, model routing, MCP tools, agent handoffs, evaluation frameworks, guardrails, and observability. Establish platform patterns, improve reliability, make technical trade-offs independently, and mentor engineers. The role requires deep Python and backend expertise, SQL proficiency, and experience with modern agent frameworks, RAG, model evaluation, and domain-driven architecture.
Top Skills: A2AClaude Agent SdkDomain-Driven DesignEmbeddingsEvent SourcingFastapiHybrid SearchLanggraphMcpPydantic AiPythonRagRerankingSQL

What you need to know about the Los Angeles Tech Scene

Los Angeles is a global leader in entertainment, so it’s no surprise that many of the biggest players in streaming, digital media and game development call the city home. But the city boasts plenty of non-entertainment innovation as well, with tech companies spanning verticals like AI, fintech, e-commerce and biotech. With major universities like Caltech, UCLA, USC and the nearby UC Irvine, the city has a steady supply of top-flight tech and engineering talent — not counting the graduates flocking to Los Angeles from across the world to enjoy its beaches, culture and year-round temperate climate.

Key Facts About Los Angeles Tech

  • Number of Tech Workers: 375,800; 5.5% of overall workforce (2024 CompTIA survey)
  • Major Tech Employers: Snap, Netflix, SpaceX, Disney, Google
  • Key Industries: Artificial intelligence, adtech, media, software, game development
  • Funding Landscape: $11.6 billion in venture capital funding in 2024 (Pitchbook)
  • Notable Investors: Strong Ventures, Fifth Wall, Upfront Ventures, Mucker Capital, Kittyhawk Ventures
  • Research Centers and Universities: California Institute of Technology, UCLA, University of Southern California, UC Irvine, Pepperdine, California Institute for Immunology and Immunotherapy, Center for Quantum Science and Engineering

Sign up now Access later

Create Free Account

Please log in or sign up to report this job.

Create Free Account