Staff Harness Engineer

About Pearl
Pearl is shaping the future of dentistry with a suite of AI solutions developed to establish higher standards of quality and care for patients worldwide. Since 2019, our team has engineered FDA-cleared computer vision capabilities for the interpretation of 2D and 3D dental imagery — industry-leading capabilities which clinicians, practice owners, labs, and insurers use to elevate the efficiency, accuracy, and consistency of dental care around the world.

At Pearl, we believe AI isn’t just what we build, it’s how we build. We’re looking for engineers who embrace AI-powered development tools to dramatically amplify their output and ship better software, faster.

The Role

We’re looking for a Staff Engineer who delivers. Someone who spots a problem, determines what needs to be done, and drives it to resolution—whether that means writing code, designing systems, untangling messy data, or pushing through blockers independently when no one’s around to ask.

You’ll own critical product areas end-to-end, working across domains where AI is the core of the product—not an afterthought.

This role sits at the center of three critical product areas:

- Real-Time Clinical AI Workflows: Build systems that capture live clinical audio, stream transcription via WebSockets, and generate structured documentation using LLMs.

- Agentic Systems: Design and improve autonomous agents that ingest events, reason using LLM tool-calling (Amazon Bedrock), and take action across internal and external systems.

- Dental Data Intelligence: Develop pipelines that ingest, normalize, and enrich fragmented data from practice management systems to power analytics and clinical insights.

Who We’re Looking For

- Own real-time transcription and LLM summarization pipelines (streaming, structured outputs, prompt design, model routing)

- Build and evolve agentic systems (tool-calling loops, MCP integrations, reasoning traces, safety guardrails)

- Develop across the stack: Node.js/TypeScript APIs, React frontends, PostgreSQL, and AWS (Lambda, SQS, S3, Bedrock)

- Design and maintain event-driven data pipelines (Kafka, SQS) across external systems

- Write integration tests first (TDD) and ensure systems are reliable and observable

- Collaborate on prompt engineering and evaluation of AI outputs

- Operate what you build: monitoring, debugging, cost management, and incident response

- Proactively identify problems and ship solutions without needing explicit direction

- Use AI assistants daily to write, debug, and refactor code

- Know how to prompt effectively and iterate toward high-quality outputs

- Critically evaluate AI-generated code

- Continuously improve workflows (prompt patterns, tooling, automation)

What You’ll Need to Succeed

- 8+ years of professional experience

- Strong ownership mindset: you take responsibility for outcomes, not just tasks

- Ability to ramp quickly in unfamiliar systems and contribute independently

- High resourceful