# Principal Engineer, LLM

Source: https://realanalystjobs.com/job/principal-engineer-llm-upstart-1e87136d
Principal Engineer, LLM at Upstart, based in USA - Remote. Experience level: 8+ Years. Posted on 19 November 2026, read from Upstart's own careers page (Greenhouse), which RealAnalystJobs re-checks daily and removes the role when it closes.

Updated 20 November 2026.

## Key facts

- Company: [Upstart](https://realanalystjobs.com/companies/upstart)
- Location: USA - Remote
- Posted: Nov 19, 2026
- Employment type: Full time
- Experience level: 8+ Years
- Source: Upstart's careers page (Greenhouse), re-checked daily

Skills: Agents, Fine-tuning, LLM, [Python](https://realanalystjobs.com/skills/python)

## About this role

About Upstart

At Upstart, we’re united by a mission that matters: to radically reduce the cost and complexity of borrowing for all Americans. Every day, we bring creativity, experimentation, and advanced AI to reshape access to credit, helping millions move forward financially with clarity and confidence.

As the leading AI lending marketplace, we partner with banks and credit unions to expand access to affordable credit through technology that’s both radically intelligent and deeply human. Our platform runs over one million predictions per borrower using more than 3,000 signals, powering smarter, fairer decisions for millions of customers. But the numbers only hint at the impact. Every idea, every voice, and every contribution moves us closer to a world where credit never stands between people and their financial progress.

We’re proudly digital-first, giving most Upstarters the flexibility to do their best work from wherever they thrive, alongside teammates across 80+ cities in the US and Canada. Digital-first doesn’t mean distant. We’re intentional about in-person connection through team onsites, planning sessions, and moments that spark creativity and trust. And whether you choose to work primarily from home or collaborate in-person from one of our offices in Columbus, Austin, the Bay Area, or New York City, you’ll have the support to work in the way that works best for you.

If you’re energized by tackling meaningful problems, excited to innovate with purpose, and motivated by work that truly matters, we’d love to hear from you.

The Team:

At Upstart, our Applied AI team's mission is threefold:

•
Agent Platform: Build and support the platform that makes it straightforward for non technical users across Upstart to build, launch, and operate AI agents (voice/chat/text) reliably.

•
Borrower and Applicant Assistant Orchestration: Build the orchestration layer behind a unified personal assistant that shares context across specialized agents, giving applicants and borrowers a cohesive, assistant-like experience.

•
Borrower-Connected Internal Workflows: Improve internal operational workflows that directly connect to applicant and borrower experiences, making them faster, smarter, and more efficient.

As Principal Engineer, LLM you will serve as a technical pathfinder and force multiplier for this team and the product squads we partner with. Rather than owning internal developer-tooling infrastructure or training foundation models from scratch, your mandate is to compress the time between an ambiguous idea and a reliable, user-facing AI system, while raising the applied AI bar across every squad you touch.

This role operates on an explicit 80/20 charter :

•
0-to-1 Product and Architecture Pathfinder (~80%): Rapidly prototype high-ambiguity bets across our agent platform, cross-agent context orchestration, borrower-facing assistant experiences, and internal workflows. Partner directly with Product and Design to validate non-deterministic UX, establish clean architectural patterns, and hand off battle-tested evaluation contracts for engineering squads to scale.

•
AI-Native Engineering Catalyst (~20%): While dedicated internal teams own Upstart's broader AI developer tooling and software-factory initiatives, you will serve as a visible practitioner on the product side. You will lead by example with agentic coding workflows and tight verification harnesses, partner with our internal tooling teams as an early adopter ("customer zero"), and help product squads adopt higher-leverage ways of working.

Because AI systems are non-deterministic, user experience is part of the architecture. Whether you are designing cross-agent handoffs, borrower-facing assistant flows, or internal operational tools, you will navigate real-world trade-offs across latency, unit economics, reliability, and user trust, and push back constructively when a simpler deterministic approach is the right call.

How you’ll make an impact

•
De-risk 0-to-1 bets across the stack: Rapidly prototype ambiguous initiatives spanning multi-agent context sharing, UX for non technical users, platform primitives for launching agents, and borrower-connected internal workflows.

•
Deliver durable evaluation contracts, not throwaway handoffs: Treat prototype code as disposable proof of concept, and hand off to engineers what they actually need to build production services with confidence: golden datasets, automated evaluation harnesses, documented failure-mode maps, latency/cost benchmarks, and clean architectural blueprints.

•
Partner cleanly from spike to production: Align early with receiving squad tech leads to surface system constraints, support joint go/no-go decisions with Engineering and Product leadership (including killing unviable bets early), and stay engaged through initial productionization to review early PRs and debug edge-case model behavior.

•
Design non-deterministic UX and orchestration together: Treat latency spikes, context loss between agents, subtle hallucinations, and fallback paths as systems design problems, shaping experiences that earn and protect borrower and operator trust.

•
Make pragmatic applied AI trade-offs: Default to the simplest reliable solution first (prompting, context engineering, deterministic guardrails), and make clear architectural calls on model routing, fine-tuning, or distillation when latency, unit economics, or reliability require it.

•
Raise the applied AI bar across squads: Model disciplined agentic coding and verification practices in your daily workflow, feed practical requirements back to internal tooling teams, and elevate engineering judgment across teams through active collaboration.

Minimum Qualifications

•
Software engineering foundation and live AI shipping: 8+ years of software engineering experience, along with hands-on experience shipping non-deterministic, user-facing LLM or AI products to real users.

•
Agentic and LLM systems architecture: Deep practical experie

Description from Upstart's public careers feed, reproduced so you can read the role here. Apply on the company's own site; Real Analyst Jobs never submits anything for you.

## How to apply

Open [this role on Real Analyst Jobs](https://realanalystjobs.com/job/principal-engineer-llm-upstart-1e87136d) and use Apply now there to reach the employer's application. The listing is re-checked against Upstart's careers page daily and removed when it closes.

## Upstart

Analyst roles on Real Analyst Jobs. [More roles at Upstart](https://realanalystjobs.com/companies/upstart)

## More like this

- [Data analyst jobs in the USA](https://realanalystjobs.com/jobs/data-analyst-jobs-in-usa)
- [Analyst job market report](https://realanalystjobs.com/analyst-job-market)
- [What analyst roles pay](https://realanalystjobs.com/blog/data-analyst-salaries)

## Sources and links

- [This role on Real Analyst Jobs](https://realanalystjobs.com/job/principal-engineer-llm-upstart-1e87136d)
- [Upstart on Real Analyst Jobs](https://realanalystjobs.com/companies/upstart)
- [All analyst jobs](https://realanalystjobs.com/jobs)
