You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Abundant

Member of Technical Staff, Alignment

  • Office
  • 6+ years

Salary

$250,000 - 450,000/ year

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The company is an applied research lab that scales reinforcement learning for agentic systems that are safe and reliable. The team includes researchers, roboticists, founders and operators, and some of its work involves the Waymo Driver.

Frontier labs run their models in environments like the ones built here, so this team sees new model behavior first.

Responsibilities

  • Keep alignment in every deliverable, including deployed code, operational runbooks and published papers.
  • Run experiments on how the environments shape agent behavior, covering reward hacking, task cheating, unsafe tool use and long-run deception, then change the environment design based on the findings.
  • Find ways to earn high scores without doing the task, close those gaps, and turn each exploit into a test the whole team runs.
  • Build monitors that review agent trajectories, red team harnesses and safety benchmarks that stay challenging as models improve, tested on real runs rather than toy ones.
  • Keep the environments sealed by working on network isolation, sandbox escapes, credential handling and how much harm an agent could cause if it turned against the system. Last summer's failures came from this area.
  • Pick a research question on oversight, control or long-horizon autonomy, answer it and publish the result as part of your regular work.
  • Decide what the company will not build, and tell partners clearly what its outputs are and are not safe for.

Requirements

  • You are an engineer first: you build your own test pipelines, pick up unfamiliar codebases quickly and find the bug hidden in a log.
  • You have deep knowledge of LLM safety, including attacks, red teaming, monitoring, control evaluations and reward hacking.
  • You can turn a vague concern about a model into a runnable experiment and state what the result does and does not show.
  • You read transcripts carefully and notice the small detail that invalidates a result.
  • You have taken research into production, especially in post-training, distillation or evaluation that other systems rely on.
  • You write clearly enough that your findings change what others do.
  • You make fast decisions on incomplete evidence and back them with data.
  • You have 8+ years of experience.
  • Preferred: published work on control, dangerous capability evaluations, oversight or interpretability.
  • Preferred: experience with RLHF or RLAIF and a clear view of how training choices affect behavior.
  • Preferred: you built or ran a public benchmark or agent task suite.
  • Preferred: you have run many agents at once using sandboxes, containers and logging.
  • Preferred: you have advised on AI safety or governance policy.

Conditions

Base salary is $250,000 to $450,000.

A cash bonus tied to project and company milestones.

Equity, including a generous early-stage grant.

US citizens or holders of a US visa only.

Benefits

  • Health, dental and vision coverage, plus flexible paid time off.

Where you’d work

From the office

The office

No visa sponsorship

About the company

Abundant

  • Industry: AI

Office in San Francisco, United States

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 20 checks run
  • 1 red flag

Still hiring?

13 checks

No red flags

How crowded?

7 checks

1 red flag

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details13 facts · Role, Location, Compensation, Employment, Company
Tech stack
  • LLMs
Seniority
Staff
Type
Full-time
Equity
Equity offered
Industry
AI
Region
United States
Show 7 more factsShow less

Role

Category
Development
Seniority
Staff
Experience
8+ years
Tech stack
  • LLMs

Location

Work model
Office
Region
United States
Office
  • San Francisco, United States
Visa sponsorship
Not sponsored

Compensation

Salary
$250,000 - 450,000 / year
Pay period
Annual
Equity
Equity offered

Employment

Type
Full-time

Company

Industry
AI

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason