Staff Software Engineer (AI)

Pendo•New York, NY
•$300,000 - $325,000•Hybrid

About The Position

Pendo’s Engineering Team builds AI products for its product experience platform, exploring, prototyping, and shipping AI-native experiences. The team works with high autonomy and builds products in areas without clear precedents. The Staff Software Engineer (AI) designs and builds production-grade AI systems, including RAG pipelines, agentic workflows, and LLM-powered product features, balancing prompting, fine-tuning, architecture, evaluation, and deployment. The role partners closely with product, design, and engineering stakeholders to identify valuable problems and communicate technical decisions. It is based in Pendo’s New York office and follows a hybrid model, with three in-office days per week unless designated remote.

Requirements

  • Deep hands-on experience building and shipping LLM-powered systems, including retrieval-augmented generation, tool use, and agent orchestration frameworks.
  • Demonstrated ability to set technical direction for AI systems across teams, establish architectural patterns, make foundational model strategy decisions, and improve AI engineering quality.
  • Experience owning outcomes across team boundaries, identifying capability gaps, aligning engineering and product, and influencing broader organizational approaches to AI.
  • Strong command of model evaluation, including designing evaluation suites, reasoning about overfitting and bias-variance tradeoffs, and detecting and mitigating hallucinations.
  • Solid understanding of modern model architectures, including transformers and diffusion models, and how to apply them.
  • Experience productionizing AI, including model deployment, monitoring pipelines, and optimizing latency, cost, and reliability in live environments.
  • Strong full-stack fundamentals and comfort working across backend and frontend systems to ship user-facing AI products.
  • Exceptional communication skills, including explaining complex technical decisions to engineers, product managers, and executives.
  • Demonstrated product judgment and ability to evaluate whether something should be built before deciding how to build it.

Nice To Haves

  • Experience fine-tuning foundation models and a clear perspective on when fine-tuning outperforms prompting-based approaches.
  • Familiarity with AI safety, guardrail frameworks, and responsible deployment practices.
  • Experience building agentic or multi-step reasoning systems using LangChain, LlamaIndex, or custom orchestration frameworks.
  • Background in a SaaS or product analytics environment where user behavior data informs AI product design.
  • Prior experience contributing to or launching a new team or product area.

Responsibilities

  • Design and build AI-native systems, including RAG pipelines, agentic workflows, and LLM-powered product features, from prototype through production.
  • Make and communicate technical decisions about prompting, fine-tuning, model strategy, and alternative approaches.
  • Define evaluation frameworks, rigorously assess model outputs, detect hallucinations, and implement robust guardrails.
  • Own AI model deployment, monitoring, latency optimization, cost management, and reliability at scale.
  • Contribute across backend and frontend systems to deliver complete, user-facing AI products.
  • Partner with product and design to frame problems before implementation, challenge poor framing, and focus the team on valuable work.
  • Stay current on AI research and tooling, and bring relevant advances to the team to raise its technical bar.
  • Set technical direction and architectural patterns for AI systems across teams, and influence broader organizational AI practices.

Benefits

  • Employer-heavy health coverage, including $0 premium options.
  • Strong 401(k) match.
  • Equity.
  • Flexible time off.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service