Six Figure Work

Member of Technical Staff, Evals

Magic

Company websitemagic.dev (Magic, opens in new tab)

Base salary $225K – $550K

Employer-published annual base salary, USD. Advertised base range in San Francisco, CA

Apply (opens in new tab)

You apply on the employer's own site. Six Figure Work does not handle applications.

  • LocationSan Francisco, CA
  • WorkplaceRemote
  • Status at last checkSource accepting applications when checked
  • Last checked (3 h ago) · observed since

About this job

Magic’s mission is to build safe AGI that accelerates humanity’s progress on the world’s most important problems. We believe the most promising path to safe AGI lies in automating research and code generation to improve models and solve alignment more reliably than humans can alone. Our approach combines frontier-scale pretraining, domain-specific RL, ultra-long context, and inference-time compute to achieve this goal.

About the role

The Evals team measures the performance and capabilities of internal and external models, helping teams across Magic make informed decisions. The team supports pretraining, RL, data, inference, and product, and sits on the critical path of many of the company's most important decisions.

As a Member of Technical Staff on Evals, you will develop new benchmarks and evaluation methodologies, run data ablations, assess dataset quality, and investigate whether our measurements accurately reflect model performance.

Sweating the details matters on this team. Many benchmarks, papers, and open-source evaluation frameworks contain subtle bugs or flawed assumptions that lead to misleading conclusions. We care deeply about correctness, reproducibility, and measurement quality.

What you'll work on

  • Design and validate new evaluations and benchmarks across model training and deployment

  • Investigate model behavior and identify gaps in existing evaluations

  • Measure dataset quality and identify opportunities to improve training data

  • Improve evaluation correctness, reproducibility, and reliability

  • Audit and improve upon public benchmarks, research papers, and open-source implementations

  • Define metrics that accurately reflect model quality

  • Build tools that make evaluation results accessible and useful across Magic

What we're looking for

  • Experience developing model evaluations, benchmarks, or ML experiments

  • Strong programming skills and experience working with machine learning systems

  • Track record of owning technical projects end-to-end

  • Strong understanding of post-training techniques and their impact on model performance

  • Skepticism toward results that cannot be reproduced, validated, or explained

  • Experience analyzing model performance and interpreting experimental results

  • Comfortable navigating ambiguity and determining whether a measurement actually captures the behavior it claims to measure

  • Commitment to raising the standard of rigor in AI evaluations

Our culture

  • Integrity. Words and actions should be aligned

  • Hands-on. At Magic, everyone is building

  • Teamwork. We move as one team, not N individuals

  • Focus. Safely deploy AGI. Everything else is noise

  • Quality. Magic should feel like magic

Magic strives to be the place where high-potential individuals can do their best work. We value quick learning and grit just as much as skill and experience.

Compensation, benefits, and perks (US)

  • Annual salary range between $225K - $550K depending on experience

  • Equity is a significant part of total compensation, in addition to salary

  • 401(k) plan with 6% salary matching

  • Generous health, dental, and vision insurance for you and your dependents

  • Unlimited paid time off

  • Visa sponsorship and relocation support for candidates moving to San Francisco

  • A small, fast-moving, highly collaborative team working on frontier AI systems

Source: Magic on Ashby · View original posting (opens in new tab)

How this pay compares

Base floor $225,000. The employer's range is $325,000 wide, 144% of the floor. Observed open for 9 days so far (since Nov 11, 2026).

How Magic pays

5 of Magic's 8 live roles on this site list a higher base floor and 1 list a lower one. Across them the median floor is $275,000; the middle half runs from $225,000 to $275,000.

Base floors of Magic's 8 live roles

Base floors of Magic's 8 live roles$100K to $125K: 12.5% (1); $125K to $150K: 0.0% (0); $150K to $175K: 0.0% (0); $175K to $200K: 0.0% (0); $200K to $225K: 0.0% (0); $225K to $250K: 25.0% (2); $250K to $275K: 0.0% (0); $275K and up: 62.5% (5)0%20%40%60%80%12%1000%1250%1500%1750%20025%2250%25062%275This job $225K
Each bar counts this employer's live roles by published base floor, in $K. The marker is this job's floor.
Table
Base floors of Magic's 8 live roles
Floor bandShareRoles
$100K to $125K12.5%1
$125K to $150K0.0%0
$150K to $175K0.0%0
$175K to $200K0.0%0
$200K to $225K0.0%0
$225K to $250K25.0%2
$250K to $275K0.0%0
$275K and up62.5%5
How this is calculated
Statistic
Employer base floor distribution
Formula
count of the employer's open roles in each $25K band of published base floor / its open roles
Denominator
8 open public roles at this employer
Sample size
8
Hidden when
this employer has fewer than 5 roles
Calculation version
jobpage-analysis-v1
Data as of
current
Employer set
Open jobs on this site that publish a base salary of $100,000 or more
This range next to 6 other live Magic roles with the nearest advertised base floor
Chart as a table
This range next to 6 other live Magic roles with the nearest advertised base floor
RolePublished base
Member of Technical Staff, Evals (this listing)$225K - $550K
Member of Technical Staff, Security Engineer$225K - $550K
Member of Technical Staff, RL Research & Environments$275K - $550K
Research Engineer$275K - $550K
Member of Technical Staff, Inference & RL Systems$275K - $550K
Member of Technical Staff, Kernels$275K - $550K
Member of Technical Staff, Pretraining Systems$275K - $550K

Same $100K to $400K scale as every card. All Magic roles · How to read the bar

Observed changes

  1. First observed on the employer's board, already publishing a qualifying base salary
  2. Stopped meeting the published-salary criteria
  3. Began meeting the published-salary criteria
Observed since
Employer-stated posting date
2026-11-11
Where this pay comes from

Location as the employer wrote it: San Francisco • Remote

USD 225,000 – 550,000 · 1 YEAR · Salary

Method
Structured pay field published by the employer
Checked
Rule set
us-base-v2

The employer's job board publishes this pay as a dedicated data field. We read the field directly; no interpretation was needed.

What we verified

  • The pay figures come from the employer's own listing, quoted exactly above.
  • The pay is an annual base salary in US dollars with a minimum of at least $100,000.
  • The role was publicly listed on the employer's job board when last checked.

We do not verify what the employer will actually offer, whether the employer is still recruiting for the role, or anything beyond what the employer published. Full methodology.

Get Six Figure Work by email

Pick what you want. Nothing is selected for you unless it matches the page you are on, and nothing is sent until you confirm from a link we email you.

What would you like to receive?

A short weekly note on what employer-published pay data shows: who pays what, where, and what is changing. Once a week.

Practical notes for job seekers: interviewing, applying for six-figure roles, and making an upward move. About twice a month.

New jobs that match a search you choose. Every job listed has an employer-published base salary of $100,000 or more. At most one email a day (or weekly, your choice). Nothing is sent on days with no new matches. Alerts cover every new job, because this page has no filters.

We email you only after you confirm from a link we send to this address. We do not sell or share your address. Every email has a one-click unsubscribe link. How we handle your email.