Post-Training Applied Researcher

Baseten

. Design and run post-training pipelines using SFT, GRPO, DPO, RLVR, reward function engineering, and synthetic data generation .

Posted 10/7/2026full-timeSan Francisco • California • United StatesMid-LevelSenior💰 $200,000 - $275,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in training Large Language Models (LLMs) using reinforcement learning techniques, with a strong focus on reward engineering and multi-turn agent environments. Proficient in designing and analyzing training pipelines and experiments across various domains, including healthcare and legal.

Highest-signal resume keywords

Training LLMs With Reinforcement LearningReward EngineeringMulti-Turn Agent EnvironmentsProduction ML SystemsPublications At NeurIPS, ICML, Or ICLR

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

SFTGRPODPORLVRReward Function EngineeringSynthetic Data GenerationDataset ConstructionTrainingEvaluationDeployment

Tools & Technologies

RL Training FrameworksBaseten's Open-Source Training Libraries

Industry Keywords

HealthcareCode GenerationLegal DomainsReward LoopsDistribution ShiftEnd-To-End Training ExperimentsReward HackingImportance Sampling DriftAdvantage Estimation Instabilities

About the role

Key responsibilities & impact

Design and run post-training pipelines using SFT, GRPO, DPO, RLVR, reward function engineering, and synthetic data generation
Build task-specific training environments and evaluations for healthcare, code generation, and legal domains
Develop multi-turn tool-use, sandboxed-execution, and agentic workflows
Work directly with customers to translate production data into training signal
Design reward loops from real usage patterns and handle distribution shift
Run and analyze end-to-end training experiments
Diagnose reward hacking, importance sampling drift, and advantage estimation instabilities
Publish findings at top venues
Contribute to Baseten's open-source training libraries

Requirements

What you’ll need

Hands-on experience training LLMs with reinforcement learning
Understanding of GRPO or PPO, including group advantage computation, clipped objectives, and KL penalty design
Strong intuition for reward engineering
Experience building multi-turn agent environments with tool use
Comfort across dataset construction, training, evaluation, and deployment
Experience with production ML systems
Preferred: experience with RL training frameworks
Preferred: publications at NeurIPS, ICML, or ICLR focused on RL for LLMs, reward modeling, or alignment

Benefits

Comp & perks

Competitive compensation, including meaningful equity
(U.S. only) 100% coverage of medical, dental, and vision insurance for employee and dependents
Flexible PTO policy including company wide Winter Break
Paid parental leave
Fertility and family-building stipend through Carrot
(U.S. only) Company-facilitated 401(k)
Exposure to a variety of ML startups, offering learning and networking opportunities