Research Engineer: RL & Post-Training LLM Systems
Preference Model
Preference Model is seeking Research Engineers or Research Scientists to advance self-directed learning in AI. The role involves training and evaluating models within proprietary RL environments and optimizing ML infrastructure. Candidates will benefit from competitive compensation, ownership in a fast-paced startup, and support for personal growth. Experience in Python, PyTorch, or JAX, along with RL training frameworks, is desired. The opportunity is a unique blend of research and engineering within a dynamic team. #J-18808-Ljbffr Preference Model
Vacancy posted 3 days ago
Similar jobs that could be interesting for youBased on the Research Engineer: RL & Post-Training LLM Systems in San Francisco, CA vacancy
- ...Research Scientist, Research Engineer, AI Systems EngineerThe Recursive Self-Improvement... ...designing evaluations, and training models to develop... ..., synthetic data, RL environments, and... ...experience across LLM training, model... ...you believe this job posting is non-compliant, please...Training
OpenAI
San Francisco, CA4 days ago $264.8k - $331k
...state of the art post-training algorithms to reach... ...The Enterprise ML Research Lab works on the front... ...ML Sys Research Engineer, you'll work on... ...our next-gen Agent RL training platform,... ...to optimize our ML system. Your customer... ...least 1-3 years of LLM training in a production...TrainingFull timeScale AI
San Francisco, CA4 days ago$264.8k - $331k
...Machine Learning Systems Research Engineer, Agent Post-training - Enterprise GenAI AI is becoming vitally important in... ...the algorithms for our next-gen Agent RL training platform, support large... ...Ideally you’d have: At least 1-3 years of LLM training in a production environment...TrainingFull timeContract workFor contractorsFor subcontractorWork at officeScale LLP
San Francisco, CA17 hours ago- Socket.dev is seeking a research-minded ML engineer to build systems that turn powerful pre-trained models into aligned,... ...reward modeling, and RL at scale, collaborating... ...across teams to push post-training capabilities.... ...experience with large-scale LLM training, and a track...Training
- ...interpretable, and steerable AI systems. We want AI to be safe and... ...growing group of committed researchers, engineers, policy experts, and... ...the cutting-edge systems that train AI models like Claude. You're... ...distributed systems Large scale LLM training Python...TrainingFull timeWork at officeVisa sponsorshipFlexible hours
Anthropic
San Francisco, CA1 day ago - ...interpretable, and steerable AI systems. We want AI to be safe... ...group of committed researchers, engineers, policy experts, and... .... About the role The RL Velocity team owns the... ...iterate quickly on training runs. As a Research... ...(RL, pre-training, or post-training) Familiarity...TrainingRemote jobWork at officeVisa sponsorshipFlexible hours
$165k - $310k
Senior Research Engineer, LLM Training & Post-Training New York, New York, United States; Remote; San Francisco, California, United States; Seattle,... ...end platform for developing, training, and deploying AI systems—designed to take ideas from research to production with...TrainingFor contractorsFor subcontractorWork at officeRemote workWork from homeFlexible hours2 days per week$189.6k - $237k
...large language model training and inference. The... ...powering MLEs, researchers, data scientists and... ...and evaluation of LLM's, as well as... ...excitement about system optimizationExperience... ...systemsStrong software engineering skills, proficient... ...expertise in post-training methods &...TrainingFull time$350k
...interpretable, and steerable AI systems. We want AI to be safe... ...group of committed researchers, engineers, policy experts, and... ...systems. About the RL Teams Our... ...RL infrastructure and training methodologies Enhancing... ...Familiarity with LLM training methodologies...TrainingFull timeWork at officeVisa sponsorshipFlexible hours- ...interpretable, and steerable AI systems. We want AI to be... ...group of committed researchers, engineers, policy experts, and... .... About the RL Teams Our... ...infrastructure and training methodologies... ...reinforcement learning, RLHF, post-training, or LLM finetuning Built...TrainingFull timeWork at officeVisa sponsorshipFlexible hours
$110.7k - $379.2k
Position Summary Research Engineer — Post-Training & Small Language Models (SLMs)... ...Americans rely on a healthcare system whose decision-making has... ...using verifiable-reward RL — designing reward signals... ...frameworks such as vLLM, TensorRT-LLM, or TGI. Small language...TrainingLocal areaVisa sponsorship$227.2k - $284k
...develop reliable AI systems for the world’s... ...applied ML research, design, and... ...Learning Research Engineer, you will... ...This could mean training and fine-tuning... ...online or offline RL — and validate... ...training methods, LLM alignment, or... ...displayed on each job posting reflects the...TrainingFull time- ...and operate end-to-end LLM evaluation systems, including runs,... ...Collaborate with AI researchers, applied AI teams, and... ...align evaluations with training objectives. Own benchmarking... ...experience on a post-training or... ...generation, rubric design, or RL-style workflows using...TrainingFull timeWork at officeRelocation package
Mercor
San Francisco, CA4 days ago - ...measure impact on model performance. You will collaborate with domain experts to design data pipelines, run RL experiments, and translate capability goals into training environments and evaluations, joining a fast-growing team at the forefront of responsible #J-18808-...Training
- Black Forest Labs is recruiting a Member of Technical Staff - Research Engineer to own and optimize large-scale generative-model training systems in a hybrid SF/remote setting. You’ll work closely with researchers to push performance, memory footprint, and stability across...TrainingRemote work
- Frontier Arc in San Francisco seeks a Research Engineer to push the core RL research agenda. You’ll own the end-to-end loop—from designing policies to training, evaluation, and interpretation—working on a proprietary simulator that aims to replace costly real-world data...Training
- ...Role We're hiring a Research Engineer to join our... ...parts ML research and systems engineering. You'll... ...be evaluated and trained against. What You'... ...Design and build RL environments for specific... ...cost tracking Run post-training... ...reinforcement learning and LLM post-training (...TrainingRelocation
$180k - $340k
...Research EngineerYou'll own the quality of AI across... ...creates. As our Research Engineer, you'll design... ...years working with AI systems, with demonstrated experience... ...prompt engineering, LLM experimentation, and systematic... ...spacesExperience with post-training techniques for LLMs...TrainingFull timeWork at officeWork from homeGamma
San Francisco, CA17 hours ago- ...Research EngineerLotus Health is a groundbreaking primary... ...ex-founders and engineers who have built and scaled... ...reasoning and agentic systems that power Lotus. You will... ...dataset curation, model training and evaluation, retrieval... ...shipping applied ML or LLM features to real users,...Training
Lotus Health
San Francisco, CA17 hours ago - HeyMilo AI is hiring a Research Engineer to join our Applied AI team in San Francisco. You’ll design... .... The role blends ML research with systems engineering, collaborating directly with... ...to reproducible environments for training and evaluation. #J-18808-Ljbffr HeyMilo...Training
- ...Research EngineerHUD is building infrastructure to create RL training data and evals for frontier AI agents, as well as a marketplace to sell these to frontier labs... ...top VCs and were YC W25.ResponsibilitiesCreate QC systems based on true understanding and human judgement,...TrainingFull timeRemote workRelocationVisa sponsorship
Hud (yc W25)
San Francisco, CA5 days ago - ...slide decks — partner with research and infra to prototype, train, and deploy state-of-the-... ...training and inference for LLM-class workloads; chase... ...level PyTorch.Proven software engineer who loves ML; comfortable... ...especially user-facing, online ML systems—despite shifting...TrainingFull timeContract workShift work
SESAME
San Francisco, CA17 hours ago $200k - $350k
...spanning Ex-Moonshot (post-training & agents, diffusion model... ...technical founders, engineers that made 100+ games... ...applied AI and large-scale systems, focusing on world... ...environments. Our current research spans:Distributed... ...vision, world models, or RL systems.Strong...TrainingVisa sponsorshipRelocation packageROAM
San Francisco, CA17 hours ago$100k - $300k
...Position Overview We are hiring Research Engineers to develop scalable robotic systems aimed at achieving general-... ...and implement new algorithms for training and optimizing general-purpose robot... ...disciplines (Perception, Robotics, RL/IL, Machine Learning, etc.)....TrainingFull timeSkild AI
San Francisco, CA5 days ago- hillclimb is seeking a research engineer to work on synthetic data generation and maintain quality pipelines for RL environments. The ideal candidate will possess a strong understanding of NLP and RL techniques, alongside a solid grasp of data structures and modern programming...
$150k - $250k
...About the Role This is a Research Engineer role at an early-stage AI infrastructure... ...the technical foundation for training and evaluating frontier AI... .... What You'll Do Build systems for creating new environments... ...and evaluations for RL training, including reasoning...TrainingFull timeVisa sponsorshipClera
San Francisco, CA2 days ago- ...building next‑generation AI systems that help military... .... As an Applied AI Research Engineer, you’ll focus on human... ...pipelines, experiment with post‑training techniques, and... ...ambitious ideas in GenAI, RL, agentic workflows,... ...with PyTorch and modern LLM tooling (Transformers,...TrainingRemote workRelocation packageFlexible hours
$350k
...Research Engineer / Scientist, AlignmentSan Francisco, CAAbout... ...interpretable, and steerable AI systems. We want AI to be safe... ...safety techniques by training language models to... ...of novel LLM-generated jailbreaks.Write... ...research papers, blog posts, and talks.Run experiments...TrainingWork at officeVisa sponsorshipFlexible hoursAnthropic
San Francisco, CA17 hours ago$315k
As a Research Engineer or Research Scientist in Applied Finetuning, you will directly train the models we launch to the public via Claude.AI and... ...advancements to production systems Qualifications Have significant... ...shared codebases and RL infrastructure Authoring research...TrainingWork at officeHome officeVisa sponsorshipRelocation package- ...models, proprietary training signals, and... ...see exactly where research meets production and... ...Offline-to-online RL on multi-touch trajectories... ..., and context systems alongside elite and competitive engineering minds. Translate findings... ..., observability); post-training and model...TrainingRelocation
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Research Engineer: RL & Post-Training LLM Systems. Be the first to apply!
Related searches
- research programmer San Francisco, CA
- research engineer San Francisco, CA
- senior research engineer San Francisco, CA
- junior machine learning research engineer San Francisco, CA
- deep learning research engineer San Francisco, CA
- research software engineer San Francisco, CA
- research assistant engineering San Francisco, CA
- ai research engineer San Francisco, CA
- ultrasound research San Francisco, CA
- research editor San Francisco, CA