Lead/Senior Research Scientist (Agentic RL)

Jobgether

United States

Hybrid

USD 180,000 - 260,000

Full time

5 hours 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

Benefits offered by this job

Remote flexibility
Professional development
Annual bonus
Volunteer days and wellbeing

Job summary

Jobgether seeks a Lead/Senior Research Scientist (Agentic RL) based in the United States to advance high-performance LLMs for complex professional workflows. You will drive agentic reinforcement learning, model training and evaluation, and collaborate with product teams to translate research into production-ready capabilities.

The role emphasizes planning, long-horizon reasoning, tool use, and multi-turn interactions in real-world settings.

Qualifications

  • PhD in Machine Learning, Computer Science, or related field or equivalent experience.
  • At least three years of research experience after PhD for Lead positions; track record of leading research agendas.

Responsibilities

  • Design and develop benchmarks, training datasets, reward models, and training signals to improve model performance across complex workflows.
  • Develop methods for tasks with limited or subjective ground truth, and conduct rigorous experiments and diagnostics.
  • Translate experimental findings into measurable improvements in production models and training processes.
  • Build evaluation suites to identify strengths, limitations, and performance gaps across use cases.
  • Collaborate with research engineers, legal/tax SMEs, and product teams to translate research into practical improvements.
  • Publish research at leading conferences and define a strategic research roadmap for the team.

Skills

Python programming
PyTorch
Strong communication
Cross-functional collaboration
Experiment design
Leadership/mentoring
MoE models
Long-context reasoning
RL post-training
Code tooling familiarity

Education

PhD in Machine Learning or Computer Science

Tools

NeMo-RL
verl
OpenRLHF
TRL

Job description

This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for a Lead/Senior Research Scientist (Agentic RL) based in United States.

The Lead/Senior Research Scientist will advance the development of high-performance large language models (LLMs) designed for complex, high-stakes professional workflows. The role focuses on research and experimentation across agentic reinforcement learning, model training, and model evaluation, with particular emphasis on improving planning, reasoning, tool use, and long-horizon task execution. Working with large open-weight models, the research team applies continual learning, preference optimization, and reinforcement learning to deliver reliable, production-ready AI capabilities. The successful candidate will collaborate closely with research engineers, legal and tax subject-matter experts, and product teams to translate research findings into practical model improvements. At Lead level, the position also offers the opportunity to shape the research roadmap, mentor colleagues, and represent the team in the wider machine learning research community.

Accountabilities
  • Design and develop benchmarks, training datasets, reward models, and training signals that improve model performance across complex professional workflows.
  • Develop methods for tasks where ground truth is limited, delayed, subjective, or difficult to verify.
  • Conduct rigorous research experiments and diagnostics, including ablation studies, to distinguish algorithmic improvements from data, reward, and system-related effects.
  • Translate experimental findings into measurable improvements in production models and model development processes.
  • Build and expand model evaluation suites to identify strengths, limitations, and performance gaps across professional use cases.
  • Use evaluation results to inform training objectives, research priorities, and technical trade-offs.
  • Research and develop agentic reinforcement learning methods that improve planning, long-context reasoning, tool calling, multi-turn interactions, and long-horizon task execution within real agent environments.
  • Contribute to post-training approaches, including policy optimization, reward modeling, and the design of reliable training signals for agentic behavior.
  • Contribute to continued pre-training and post-training of open-weight models, including Direct Preference Optimization (DPO), reinforcement learning, training data design, and strategies for mitigating forgetting through replay.
  • Develop evaluation methods for complex legal, tax, and other professional workflows, including expert-annotated benchmarks, LLM-as-a-judge systems, evaluation rubrics, and human preference studies.
  • Work closely with Research Engineers to develop and improve large-scale model training and evaluation infrastructure.
  • Collaborate with legal, tax, and other professional subject-matter experts to ensure model training and evaluation reflect real-world requirements and domain-specific expectations.
  • Partner with product teams and other model users to understand adoption needs and support the integration of research outcomes into practical applications.
  • Publish research regularly at leading machine learning and natural language processing conferences and contribute to the broader research community.
  • At Lead level, define and own a research agenda, translate emerging research methods into a strategic roadmap, and mentor scientists and engineers.
  • Depending on specialization, contribute primarily to one or two of the following areas: agentic reinforcement learning, model training, or model evaluation.
Requirements
  • Education: PhD in Machine Learning, Computer Science, or a related discipline, or equivalent practical research experience.
  • Research and development experience: Hands-on experience in LLM post-training and/or model evaluation, preferably at the scale of frontier model development.
  • Technical skills: Strong Python programming skills and practical experience with PyTorch.
  • Research impact: Demonstrated research contributions through publications at leading venues such as NeurIPS, ICML, ICLR, ACL, EMNLP, or COLM, and/or direct contributions that have influenced an LLM development cycle.
  • Cross-functional collaboration: Experience working with researchers, engineers, and subject-matter experts to turn research ideas into practical training datasets, evaluation frameworks, or production capabilities.
  • Communication: Excellent written and verbal communication skills, with the ability to explain complex research findings and collaborate effectively across disciplines.
  • Adaptability: Comfort working in a fast-paced, evolving research environment where problems may be ambiguous and priorities can change.
  • Lead-level requirements: For Lead positions, at least three years of research experience after completing a PhD, a track record of leading research agendas through to published or deployed outcomes, and experience mentoring or supervising researchers.
  • Preferred reinforcement learning frameworks: Experience with RL post-training frameworks such as NeMo-RL, verl, OpenRLHF, or TRL.
  • Preferred evaluation frameworks: Familiarity with tools such as Inspect or lm-evaluation-harness.
  • Reward and evaluation design: Experience building LLM-as-a-judge systems, rubric-based reward models, or evaluation pipelines, including methods for measuring their reliability.
  • Advanced model architectures: Familiarity with Mixture-of-Experts (MoE) models or long-context architectures.
  • Professional-domain AI: Experience working with legal, tax, or other professional domains where outputs may be difficult to verify, particularly in grounding and citation.
  • Experimental methodology: Knowledge of rigorous experimental design and best practices for collecting and using human-generated data.
  • AI-assisted development: Familiarity with AI-assisted coding tools and the use of coding agents at scale.
Benefits
  • Competitive compensation: For Ontario, Canada, the advertised annual base salary range is CAD $100,000–$145,000.
  • Annual bonus: The role may be eligible for an annual performance bonus based on a combination of individual and enterprise results.
  • Remote flexibility: Remote working arrangement, with flexible workplace policies and the opportunity to work from anywhere for up to eight weeks per year.
  • Work-life balance: Flexible vacation, two company-wide mental health days annually, and access to the Headspace app.
  • Retirement and financial wellbeing: Retirement savings programs and resources supporting financial wellbeing.
  • Professional development: Continuous learning opportunities, skills development programs, and tuition reimbursement.
  • Employee incentive programs: Access to additional incentive and recognition opportunities.
  • Wellbeing support: Resources and programs supporting mental, physical, and financial health.
  • Community involvement: Two paid volunteer days annually, opportunities for pro bono consulting, and participation in social impact and environmental initiatives.
  • Inclusive culture: A globally collaborative environment focused on inclusion, belonging, flexibility, and professional growth.
  • Research and innovation: Opportunities to publish at leading research venues, work with advanced LLM technologies, and contribute to AI systems supporting complex professional workflows.

We appreciate your interest and wish you the best!

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Lead/Senior Research Scientist (Agentic RL)
Lead/Senior Research Scientist (Agentic RL)

Thomson Reuters • New York (NY)

On-site
USD 180,000 - 250,000
Lead/Senior Research Scientist (Agentic RL)
Lead/Senior Research Scientist (Agentic RL)

Thomson Reuters Corp. • Town of Ontario (NY)

Remote
USD 127,000 - 237,000
Flexible vacation
Mental Health Days
Tuition reimbursement
Lead/Senior Research Scientist (Agentic RL)
Lead/Senior Research Scientist (Agentic RL)

Thomson Reuters • United States

Remote
USD 140,000 - 210,000
Flexible vacation
Mental health days off
Headspace access
+1
Senior AI Engineer (LLM Training & RLHF) - Remote
Senior AI Engineer (LLM Training & RLHF) - Remote

Prolific • Mesa (AZ)

On-site
USD 140,000 - 230,000
Machine Learning Engineer, LLM Post-Training
Machine Learning Engineer, LLM Post-Training

News Break • Mountain View (CA)

On-site
USD 150,000 - 230,000
Health, dental, and vision care for you and your family
Top-tier 401(K) plan with company matching
Paid time off and paid holidays
+2
Member of Technical Staff [Research]
Member of Technical Staff [Research]

NeoCognition • Palo Alto (CA)

On-site
USD 120,000 - 150,000
Member of Technical Staff, Reinforcement Learning
Member of Technical Staff, Reinforcement Learning

True Talent Solutions Partners • United States

Remote
USD 250,000 - 400,000
AI/LLM Engineer (Model Fine-Tuning & Conversational AI)
AI/LLM Engineer (Model Fine-Tuning & Conversational AI)

Salveinno • United States

Remote
USD 90,000 - 134,000
Fully remote in Europe
B2B contractor arrangement
Health allowance
+8
Machine Learning Research Scientist – LLMs (Remote | $100 –$120/hr)
Machine Learning Research Scientist – LLMs (Remote | $100 –$120/hr)

Synthires • United States

Remote
USD 138,000 - 165,000
Weekly payments
Remote work
AI/LLM Engineer (Model Fine-Tuning & Conversational AI)
AI/LLM Engineer (Model Fine-Tuning & Conversational AI)

Salve.Inno • United States

Remote
USD 120,000 - 180,000
Remote Europe
B2B contractor
Paid leave 20 days
+9