Postdoc Researcher: RLHF & Epistemic AI for LLMs

University of Virginia

Charlottesville (VA)

On-site

USD 62,000 - 67,000

Full time

3 days ago
Be an early applicant

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

The University of Virginia Department of Systems and Information Engineering seeks postdoctoral researchers to advance statistical and algorithmic foundations for RLHF and epistemic control of LLMs. The role emphasizes training LLMs to reason reliably, handle uncertainty, and adapt to user tasks.

Starting Jan 1, 2027 for one year with possible renewal; salary range $62,000–$67,000 annually. The position involves theory, algorithms, and empirical validation, with collaboration across ML, AI,

Qualifications

  • Strong background in theoretical ML, statistical learning theory, optimization, or reinforcement learning.
  • Experience establishing theoretical guarantees for deep-learning or high-dimensional models.
  • Experience implementing and evaluating large models with common ML frameworks.

Responsibilities

  • Develop theory, algorithms, and empirical evaluations for RLHF and epistemic control.
  • Establish statistical or algorithmic guarantees where appropriate.
  • Design and implement empirical evaluations using modern ML frameworks and open-source LLMs.
  • Prepare research papers for publication in top ML/AI/statistics venues.
  • Collaborate with faculty, graduate students, and other researchers.
  • Contribute to a broader research program on reliable and human-centered AI.

Skills

Theoretical ML
Statistical learning theory
Optimization
Reinforcement learning
LLM alignment

Education

PhD in EE/CS/Stats/OR/Systems

Tools

PyTorch
JAX
TensorFlow

Job description

The University of Virginia Department of Systems and Information Engineering seeks postdoctoral researchers to advance statistical and algorithmic foundations for RLHF and epistemic control of LLMs. The role emphasizes training LLMs to reason reliably, handle uncertainty, and adapt to user tasks.

Starting Jan 1, 2027 for one year with possible renewal; salary range $62,000–$67,000 annually. The position involves theory, algorithms, and empirical validation, with collaboration across ML, AI,

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Research Associate in Systems and Information Engineering
Research Associate in Systems and Information Engineering

University of Virginia • Charlottesville (VA)

On-site
USD 62,000 - 67,000
Artificial Intelligence Researcher
Artificial Intelligence Researcher

Cerebro • San Francisco (CA)

On-site
USD 160,000 - 230,000
Research Associate in Computer Science
Research Associate in Computer Science

University of Virginia • Charlottesville (VA)

On-site
USD 52,000 - 56,000
Postdoc: ML Systems for Secure, Privacy-Aware LLMs
Postdoc: ML Systems for Secure, Privacy-Aware LLMs

State of Virginia • Virginia

On-site
USD 60,000 - 70,000
Postdoc: ML/LLM Systems & Privacy
Postdoc: ML/LLM Systems & Privacy

University of Virginia • Charlottesville (VA)

On-site
USD 52,000 - 56,000
Staff ML Engineer - RL for LLMs & Generalization
Staff ML Engineer - RL for LLMs & Generalization

Cohere • United States

Hybrid
USD 150,000 - 210,000
Remote-friendly
LLM Post-Training Research Scientist (SFT/RLHF)
LLM Post-Training Research Scientist (SFT/RLHF)

Scale AI, Inc. • New York (NY)

On-site
USD 181,000 - 226,000
Health, dental and vision coverage
Retirement benefits
Learning & development stipend
+2
Research Associate In Computer Science Charlottesville
Research Associate In Computer Science Charlottesville

State of Virginia • Virginia

On-site
USD 60,000 - 70,000
LLM Post-Training Research Scientist (SFT & RLHF)
LLM Post-Training Research Scientist (SFT & RLHF)

Scale AI, Inc. • New York (NY)

On-site
USD 181,000 - 226,000
Health, dental & vision coverage
Retirement benefits
Learning and development stipend
+2
LLM Post-Training Scientist - SFT & RLHF
LLM Post-Training Scientist - SFT & RLHF

Scale AI, Inc. • San Francisco (CA)

On-site
USD 181,000 - 226,000
Health benefits
Retirement plan
Learning stipend
+2