Product Lead, Rippling AI – Agent Harness & Runtime

Why this role exists

Model quality is converging across providers. The differentiator that remains and compounds is the layer around the model: how it holds context recovers from tool failure knows what its allowed to touch and gets measurably better over time without a human rewriting its instructions every week. That layer is the harness. It is the difference between a demo and a system you can put in front of a customers payroll data.

Were hiring the PM who owns that layer for Ripplings agents: our own harness the memory systems that feed it and the self-improvement loop that tunes it. This is not a PM role bolted onto an engineering teams backlog. You will make build-vs-buy calls on runtime architecture define what done means for a memory system and be the person who can sit in a design review with staff engineers and catch a bad abstraction before it ships.

What youll own

Harness: Inform the architecture that turns a model into a worker including how it plans calls tools interprets results and decides to continue retry or escalate. Youll define the contract between orchestration and the harness any required guardrails and how to refine the harness to support the agents were building across Rippling.

Memory: Working memory inside a single run episodic memory across sessions understanding and defining the boundary between what belongs in context versus what belongs in a tool call. Youll help define what gets persisted what gets compacted and what gets forgotten on purpose.

Self-improvement: The feedback loop that makes the harness better without a human editing prompts by hand eval-driven tuning trajectory review counterfactual benchmarking against prior versions. You own the definition of improved: task completion rate escalation-to-human rate cost and latency per successfully completed task and regression rate on the eval suite you help build.

Infrastructure: Sandboxing and execution environments permission tiers and connector-level ACLs credential handling so the model never sees a raw secret and the observability stack that lets an engineer answer why did this agent do that six weeks after the fact.

New platform capabilities: As the core harness matures youll extend it into computer-use and autonomous web/research capabilities agents that navigate interfaces without an API and multi-step research tasks that synthesize across sources.

Who you are

• A former software engineer-turned-PM with 5 years of combined experience. Youve shipped production systems yourself not just specced them.
• Youve built or shipped agentic systems in production not just prototyped them in a notebook. You can speak precisely about the difference between an agent framework (the blueprint) and a harness (the runtime that actually executes and recovers) and you dont use the terms interchangeably.
• You think in state machines and failure modes by default: what happens when the tool call times out when the model hallucinates a tool that doesnt exist when two agents claim the same lock. Youve debugged distributed systems before you ever wrote a spec for one.
• You have a strong point of view on evals and can design a benchmark that predicts production behavior instead of rewarding overfit.
• Youre fluent in the concepts this space actually uses day to day: context window management tool orchestration RAG vs. semantic vs. episodic memory OAuth grant types and blast radius sandbox isolation RL/fine-tuning vs. non-parametric adaptation.
• You default to writing the design doc yourself when the team is moving too fast to wait for consensus and youre just as comfortable being told your design is wrong by an engineer with more context.

What this role is not

It is not a backlog-grooming PM seat on an existing engineering-driven roadmap. It is also not a research-adjacent role for someone who wants to stay theoretical. You will be accountable for what ships and what it costs when its wrong.

Additional Information

Rippling is an equal opportunity employer. We are committed to building a diverse and inclusive workforce and do not discriminate based on race religion color national origin ancestry physical disability mental disability medical condition genetic information marital status sex gender gender identity gender expression age sexual orientation veteran or military status or any other legally protected characteristics Rippling is committed to providing reasonable accommodations for candidates with disabilities who need assistance during the hiring process. To request a reasonable accommodation please email

Rippling highly values having employees working in-office to foster a collaborative work environment and company culture. For office-based employees (employees who live within a defined radius of a Rippling office) Rippling considers working in the office at least three days a week under current policy to be an essential function of the employees role.

This role will receive a competitive salary benefits equity. The salary for US-based employees will be aligned with one of the ranges below based on location; see which tier applies to your location here.

A variety of factors are considered when determining someones compensation including a candidates professional background experience and location. Final offer amounts may vary from the amounts listed below.