Research Scientist, Agent Reasoning San Francisco $260,000 – $340,000

Pazau, Inc.; San Francisco (CA); Presencial; USD 260 000 - 340 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Equity in Pazau

Medical and dental coverage

401(k) match

Learning stipend

Conference travel

Paid time off

Resumo da oferta

Pazau, Inc. is seeking senior researchers to design planning and tool-use strategies for multi-turn agent systems. You will shape approaches that ensure adherence to procedures and robust decision-making in customer interactions.

The role emphasizes planning, reasoning, and safety, with equity in Pazau and a strong engineering environment. You will collaborate with product and research teams in San Francisco, contributing to production-ready research.

Qualificações

• PhD or equivalent in ML/NLP or related field.
• Track record of research on LLM agents, planning, tool use or reasoning.
• Strong engineering skills; prototyping in Python and shipping with production engineers.

Responsabilidades

• Research methods to improve Procedure adherence and Action accuracy without customer-data training.
• Design reasoning strategies for long, multi-turn conversations with changing customer needs.
• Build calibrated confidence signals to decide when to act, seek approval, or escalate.
• Collaborate with Evaluation to turn research into shipped improvements measured by customer resolution rates.

Conhecimentos

PhD in ML/NLP

Research on LLM agents

Python programming

Planning and tool use

Policy adherence

Formação académica

PhD or equivalent

Ferramentas

Python

Descrição da oferta de emprego

About the role

Pazau Agent 3 plans multi-step work: it checks eligibility, calls three systems, asks for approval and then confirms with the customer, all while following a Procedure a CX manager wrote in plain English. We don't train foundation models on customer data, so our research focuses on the layer above them: planning, tool use, policy adherence and knowing when to hand off.

The base salary range for this role is $260,000 – $340,000. Final offers depend on level and location, and every offer includes equity.

What you'll do

• Research methods that improve Procedure adherence and Action accuracy without customer-data training


• Design reasoning strategies for long, multi-turn conversations where the customer changes their mind halfway through


• Build calibrated confidence signals that decide when the agent acts, asks for approval or escalates to a human


• Work with the Evaluation team to turn research wins into shipped improvements, measured in customer resolution rates

What you'll bring

• A PhD or equivalent research experience in machine learning, NLP or a related field


• A track record of research on LLM agents, planning, tool use or reasoning


• Strong engineering skills. You'll prototype in Python and ship alongside production engineers


• Interest in problems where being right 97% of the time is not good enough

Nice to have

• Publications at NeurIPS, ICML, ACL or similar


• Experience with RL from environment feedback or simulation-based training


• Worked on AI safety, calibration or interpretability


• Medical, dental and vision for you and your dependents, with 100% of premiums covered


• Equity in Pazau, with a 10-year exercise window after you leave


• 16 weeks of fully paid parental leave for every parent


• 401(k) with a 4% match


• $2,000 a year for learning, plus conference travel when you're speaking


• Four weeks of paid time off, plus a company-wide week off at the end of December


• Recruiter call (30 min). We walk through the role, compensation and timeline, and answer your questions first.


• Hiring manager conversation (45 min). A conversation about work you're proud of and the problems this team owns.


• Research talk (60 min). You'll present your past work to the AI team, followed by a technical discussion.


• Final interviews (3–4 hours, virtual or on-site). Three or four conversations with the people you'd work with every day, including one cross-functional partner.


• Founder conversation and references. A 30-minute conversation with Amara or Lukas, then two references you choose.

Most candidates go from first call to offer in three to four weeks. You'll hear back from us within three business days after every stage, and every candidate who reaches final interviews gets written feedback.

Sound like your next job?

We reply to every application within five business days.