Machine learning researcher (PhD): evaluation design and red-teaming

HUMXN

United States

Remote

USD 207,000 - 344,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Humxn is seeking experts to perform evaluation tasks remotely in the United States, with 5 to 20 hours per week. You will design prompts, assess model reasoning, and review research code and experiments. Payouts occur via Stripe after identity verification; take part in a paid calibration task first.

Rates are $150–$250 per hour, with higher rates for more complex projects based on track record. The work is remote and on your own schedule, and each piece of work traces to a verified expert.

Qualifications

  • PhD in computer science, statistics, or related field with publications in ML, NLP, systems or theory.
  • Strong engineering skills.
  • Experience training or evaluating large models is a plus.

Responsibilities

  • Design evaluation tasks that distinguish genuine capability from pattern matching.
  • Write adversarial and edge-case prompts in your field.
  • Review model-generated research code, experiments, and claimed results.
  • Grade reasoning on systems, theory and algorithms problems.

Skills

Strong engineering skills
Experience training or evaluating LLMs

Education

PhD in computer science or statistics

Job description

Pay: $150–$250/hr

The work

Design evaluation tasks that distinguish genuine capability from pattern matching; write adversarial and edge-case prompts in your specialism; review model-generated research code, experiments and claimed results; grade reasoning on systems, theory and algorithms problems.

Who it suits
  • PhD in computer science, statistics or a related field with publications in machine learning, NLP, systems or theory.
  • Strong engineering skills; experience training or evaluating large models a plus.
How it works
  • 5 to 20 hours a week suits most people; the work is remote and on your own schedule.
  • We verify your credentials, licence or degree and your identity before any paid work. Every piece of work traces to a named, verified expert.
  • A paid calibration task on the project's own guidelines comes first.
  • You are paid at the rate on this page for every hour of work that passes review. Rates rise with the difficulty of the project and your track record.

HUMXN is a new expert network (launched 2026). Payouts go through Stripe after identity and tax verification. Never pay to apply.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Machine Learning Researcher
Machine Learning Researcher

Micro1 • United States

Remote
USD 83,000 - 165,000
Remote ML Researcher: Evaluation & Adversarial Research
Remote ML Researcher: Evaluation & Adversarial Research

Humxn • United States

Remote
USD 207,000 - 344,000
Machine Learning Expert
Machine Learning Expert

Alpheva • United States

Remote
USD 248,000 - 317,000
Machine Learning Researcher
Machine Learning Researcher

micro1 Inc. • United States

Remote
USD 83,000 - 165,000
Machine Learning Research Evaluation Expert
Machine Learning Research Evaluation Expert

OpenTrain AI, Inc. • United States

Remote
USD 131,000 - 186,000
Machine Learning Researcher (MSc. or PhD)
Machine Learning Researcher (MSc. or PhD)

SaidGig • United States

Remote
USD 83,000 - 165,000
ML Engineer (MSc. or PhD)
ML Engineer (MSc. or PhD)

Micro1 • United States

Remote
USD 83,000 - 165,000
Machine Learning Researcher (MSc. or PhD)
Machine Learning Researcher (MSc. or PhD)

Micro1 • United States

Remote
USD 83,000 - 165,000
Machine Learning Researcher (MSc. or PhD)
Machine Learning Researcher (MSc. or PhD)

Softechub • United States

Remote
USD 83,000 - 165,000
Flexible schedule
Remote worldwide
Machine Learning Researcher (Remote | $60–$120/hr)
Machine Learning Researcher (Remote | $60–$120/hr)

Synthires • California

Remote
USD 83,000 - 165,000
Remote work (Worldwide)
Flexible schedule
Output-based payment