3 months ago
Base Salary
$209k - $235k/yr
Responsibilities
- Design and build RAG pipelines, agentic workflows, and LLM-powered features from prototype through production.
- Make technical decisions about prompting, fine-tuning, and alternative tools while clearly communicating tradeoffs.
- Define evaluation frameworks, instrument model outputs, detect hallucinations, and implement production-ready guardrails.
- Own model deployment, monitoring, latency optimization, cost management, and reliability at scale.
- Work across backend and frontend systems to ship complete AI-powered user experiences.
- Partner with product and design to frame problems and determine what should be built.
- Track research and tooling developments involving transformers, diffusion architectures, orchestration frameworks, and emerging agent patterns.
- Set technical quality standards, identify problems in review, and improve shared infrastructure and tooling.
Requirements
- Deep hands-on experience building and shipping LLM-powered systems, including retrieval-augmented generation, tool use, and agent orchestration frameworks.
- Strong system design expertise, including architecture selection, early failure-mode identification, and lifecycle tradeoff evaluation.
- Experience owning technical quality beyond individual features by setting standards and improving shared infrastructure and tooling.
- Strong command of model evaluation, including evaluation suites, overfitting, bias-variance tradeoffs, and hallucination detection and mitigation.
- Understanding of modern model architectures, including transformers and diffusion models.
- Experience productionizing AI through model deployment, monitoring pipelines, and latency, cost, and reliability optimization.
- Strong full-stack fundamentals across backend and frontend systems for shipping user-facing AI products.
- Exceptional communication skills for explaining complex technical decisions to engineers, product managers, and executives.
- Demonstrated product thinking and the ability to evaluate what should be built before deciding how to build it.
- Experience fine-tuning foundation models is preferred.
- Familiarity with AI safety, guardrail frameworks, and responsible deployment practices is preferred.
- Experience building agentic or multi-step reasoning systems with LangChain, LlamaIndex, or custom orchestration frameworks is preferred.
- Background in a SaaS or product analytics environment is preferred.
- Prior experience contributing to or launching a new team or product area is preferred.
Benefits
- Hybrid work culture with 3 days per week in the office unless designated remote
- Employer-heavy healthcare coverage, including $0 premium options
- Strong 401(k) match
- Equity
- Flexible time off
Categories
About Pendo
The only official Pendo LinkedIn account. Pendo’s mission is to elevate the world’s experience with software. Pendo’s product experience platform allows companies to make product intelligence actionable with speed and scale, giving rise to a new generation of companies that put product at the center of everything. Pendo customers include the world’s leading companies, including Verizon, Morgan Stanley, LabCorp, OpenTable, Okta, Salesforce, and Zendesk. Through Mind the Product and customer communities, sponsored events and podcast, Pendo aims to support the success of product and digital leaders everywhere. Pendo is headquartered in Raleigh, North Carolina and has offices around the world.