Post-Training Research Engineer: RLHF, Evaluation & Stats
present of AI
Cognition in San Francisco is seeking a leader for the post-training loop of coding agents, responsible for building training recipes, designing evals, and diagnosing why results look strange. The role requires depth in preference learning and reward methods such as RLHF, plus solid statistics to tell true effects from noise. The ideal candidate has trained large models across many GPUs and has published or open-source ML work. Priorities may shift quickly, demanding clear judgment. #J-18808-Ljbffr
Vacancy posted 2 days ago
Similar jobs that could be interesting for youBased on the Post-Training Research Engineer: RLHF, Evaluation & Stats in San Francisco, CA vacancy
- ...Research Engineer, Post-Training Model Evaluations Investigate model quality during production post-training, maintain evaluation coverage and explain regressions to research teams. Vacancy announcement Who this suits: Individual qualified applicant Accepting...TrainingWork at office
Prof Rod
San Francisco, CA2 days ago - ...compute, environments, evaluations, secure sandboxes, high-performance training, and deployment into one... ...full-stack system for post-training at frontier scale... ...tasks like autonomous research, and the full-stack... ...Requirements Strong software engineering skills in Python and...TrainingRemote workVisa sponsorshipRelocation packageFlexible hours
Prime Intellect, Inc.
San Francisco, CA2 days ago - ...daily U.S. X-rays. Our research team brings experience... ...exceptional Research Engineer or Research Scientist... ...we curate data and evaluate frontier AI models for... ...determine the quality of our training data and how we... ...foundation models, VLMs, and post-training methods. This...Training
Alt
San Francisco, CA1 day ago $231k - $340k
...started. Role Overview Post-training is how Harvey turns expert... ...work. We are looking for a research engineer who can help scale that... ...that are reliable enough for evaluation, efficient enough for iteration... ..., preference optimization, RLHF/RLAIF, reward modeling,...TrainingHarvey AI
San Francisco, CA4 days ago- ...foundation for agent engineering in the real world, helping... ...for building, evaluating, deploying, and operating... ...for an experienced research engineer to help make... ...selection, fine-tuning and post-training custom models. The... ...optimization, SFT, RLHF/RLAIF, or other post-...TrainingWork at officeFlexible hours
LangChain
San Francisco, CA4 days ago - ...Research Engineer Intern, Evaluations & BenchmarksLocation: San Francisco (Hybrid)TensorStax is building fully autonomous AI systems to manage and optimize... ...evaluation methodologies, reinforcement learning, and RLHF techniques.Familiarity with benchmarking language models...Internship
Tensorstax
San Francisco, CA4 days ago - ...Applied Research EngineerThe next wave of competitive... ...AI systems trained on proprietary... ...Applied Research Engineer, you'll design, train... ...design to training, evaluation, and iteration in... ...models: Fine-tune and post-train models on... ...training such as RLHF or RLAIF, or evaluation...Training
Eragon
San Francisco, CA4 days ago - ...automation for high-quality training data at scale. Expert... ...Excellence: Join a team of top researchers and engineers passionate about ethical AI... ...with human intent using RLHF, DPO, and related approaches... ...tools for collecting, evaluating, and optimizing human feedback...TrainingFlexible hours
Right Hire Consulting LLC
San Francisco, CA15 hours ago $150k - $200k
...benchmarks those labs use to train and test their models. You'd be their first engineer in San Francisco, and... ...actually got better Post-training experiments,... ..., tasks, benchmarks or evaluation harnesses with your own... ...(SFT, DPO, GRPO, RLHF or similar), ideally with...TrainingFull timeWork at officeRnb Consultancy
San Francisco, CA2 days ago- ...Research Engineer – Reinforcement LearningLocation: San Francisco (Hybrid)TensorStax... ...supervised fine-tuning (SFT) and RLHF.Design experiments to evaluate and improve the agentic capabilities... ...Points:Experience with distributed training in PyTorch (DDP, FSDP).Hands-on experience...Training
Tensorstax
San Francisco, CA4 days ago - ...We are looking for a hybrid Systems Engineer and AI Researcher to lead the development of our agent evaluation framework and post-training data pipelines. You will design sandboxed execution... ...post-training infrastructure (RLHF, Direct Preference Optimization, Process...TrainingWork at office
Hyphen Connect
San Francisco, CA4 days ago $165k - $310k
...Senior Research Engineer, LLM Training & Post-Training New York, New York, United States; Remote; San Francisco... ...models are trained, fine‑tuned, evaluated, and deployed across Lightning AI’s... ...such as continued pretraining, SFT, RLHF, preference optimization (DPO, PPO,...TrainingFor contractorsFor subcontractorWork at officeRemote workWork from homeFlexible hours2 days per weekLightning AI
San Francisco, CA19 hours ago- ...team includes ex-founders and engineers who have built and scaled... ...We are hiring a Founding Research Engineer to design, prototype... ...: dataset curation, model training and evaluation, retrieval and tool use, safety... ..., and NCPDP Background in RLHF or RLAIF, distillation,...Training
$189.6k - $237k
...large language model training and inference. The... ...powering MLEs, researchers, data scientists and... ...training and evaluation of LLM's, as well... ...systemsStrong software engineering skills, proficient... ...expertise in post-training methods &... ...instruction tuning, RLHF, tool use, reasoning...TrainingFull timeScale AI
San Francisco, CA8 days ago$250k - $350k
...combining rigorous evaluation with full-stack... ...paired with applied ML research, design, and... ...Learning Research Engineer, you will operate... .... This could mean training and fine-tuning models... ...fine-tuning (SFT, RLHF/RLAIF, reward modeling... ...on each job posting reflects the minimum...TrainingFull timeScale AI
San Francisco, CA8 days ago- ...is the world’s leading research accelerator for... ...quality data, advanced training pipelines, plus top AI... ...environments that power post-training for leading AI... ...enterprises. Our environments evaluate and improve AI models... ...includes: Software engineering environments for...TrainingContract workPart timeFor contractors
Turing
San Francisco, CA23 days ago $1,000 per month
...micro1 is the leading AI data lab for training frontier models and evaluating AI agents. Experts contribute... ...such as finance, healthcare, STEM engineering, and more. micro1 transforms that... ...layer for frontier AI. Role Title: Research Engineer - Code Generation & Model...TrainingPart timeFor contractorsRemote workmicro1
San Francisco, CA23 days ago$150k - $250k
...global social organizations.We research and deploy technologies that... ...ForAt Distyl, Research Engineers build the bridge between frontier... ...system behavior, build evaluation frameworks, and collaborate... ...ResponsibilitiesDesign and run post-training workflows that improve the behavior...TrainingWork at office3 days per weekDistyl AI
San Francisco, CA8 days ago$193.3k - $261.5k
...of this team, you will lead research and development efforts in generative... ...and deep collaboration with engineering teams to bring research into... ...data collection/annotation/evaluation web applications.* Expedite... ...transformer architecture, training/inference lifecycles, and...TrainingInternshipLocal areaFlexible hoursAmazonWebServices
San Francisco, CA7 days ago- ...Workspace.Sierra’s Applied Research team advances the quality, speed... ...of tasks. Our work spans post-training open-weight models for specialized... ....Develop, fine-tune, evaluate, and deploy models that improve... ...timeLocation TypeOn-siteDepartmentEngineeringPlatform EngineeringTrainingFull timeFlexible hours
Sierra
San Francisco, CA6 days ago - ...compute, environments, evaluations, secure sandboxes, high-performance training, and deployment into one... ...full-stack system for post-training at frontier scale... ...tasks like autonomous research, and the full-stack... ..., working with systems engineers on hardware-aware execution...TrainingRemote workVisa sponsorshipRelocation packageFlexible hours
Prime Intellect, Inc.
San Francisco, CA2 days ago $150k - $350k
...compute, environments, evaluations, secure sandboxes, high-performance training, and deployment into one... ...full-stack system for post-training at frontier scale... ...tasks like autonomous research, and the full-stack... ...researchers and infrastructure engineers to translate...TrainingRemote workVisa sponsorshipRelocation packageFlexible hoursPrime Intellect, Inc.
San Francisco, CA4 days ago$197.3k - $313.7k
...software and platform engineers to embed in our AI team... ...enable world-class research and products used by millions... ...APIs, UIs, agentic evaluators, and more.Roll out... ...tools and opt out options.Posting StatementSalesforce is... ...promotion, benefits, training, assessment of job...TrainingFull timeSalesforce
San Francisco, CA7 days ago- ...ML/AI Research Engineer — Agentic AI Lab (Founding Team) Location: San Francisco Bay Area... ...join our AI Lab and lead the design, training, evaluation, and optimization of agent-native AI... ...pipelines to optimize agent behaviors (e.g. RLHF, DPO, PPO) Establish scalable...TrainingFull time
Fabrion
San Francisco, CA4 days ago $136.44k - $265.11k
...our work here.You’ll build the datasets, evaluations, and systems that help close that gap.... ...work at the intersection of software engineering, biology, and frontier AI: finding tasks... ...with engineers, scientists, and external research partners.Desire to work in a fast-paced...Work at officeLocal areaMonday to FridayShift workBenchling
San Francisco, CA4 days ago- ...About the Role As a Research Engineer, you’ll be responsible for building... ...and roadmaps Train, fine-tune, validate, and further... ...by our customers Design evaluation protocols and benchmarks that... ...~ Prior experience post-training and deploying LLMs...TrainingWork at officeFlexible hours
Alt
San Francisco, CA4 days ago $250k
...: Transluce is a non‑profit research lab building tools for scalable... ...set industry standards for evaluation. Our tools are integrated with... ...for strong scientists and engineers to help advance our vision of... ...responsibility: Help us develop and train scalable interpretability...TrainingWork at officeVisa sponsorshipTransluce
San Francisco, CA4 days ago- ...Pantograph is training general models that start by watching internet-scale video and... ...durable robots. We're looking for a research engineer to help us train increasingly capable... ...reinforcement learning, data processing, evaluation, and the infrastructure required to...Training
Pantograph
San Francisco, CA4 days ago - ...the Team The Privacy Engineering Team at OpenAI is... ...functional engineering and research partners with the... ...Develop internal libraries, evaluation suites, and... ...insights that inform model‑training and product‑safety decisions... ...dataset curation to post‑deployment monitoring....TrainingRelocation package
The Consensus
San Francisco, CA4 days ago - ...Phonic Phonic is a product and research lab focused on powering the... ...The Role As a Research Engineer at Phonic, you'll sit at the... ...genuinely human. You'll design, train, and iterate on models across... ...the training pipelines, evaluation frameworks, and tooling that...TrainingWork at office
Mixpeek
San Francisco, CA4 days ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Post-Training Research Engineer: RLHF, Evaluation & Stats. Be the first to apply!
Related searches
- research assistant engineering San Francisco, CA
- research software engineer San Francisco, CA
- deep learning research engineer San Francisco, CA
- ai research engineer San Francisco, CA
- senior research engineer San Francisco, CA
- research engineer San Francisco, CA
- research programmer San Francisco, CA
- junior machine learning research engineer San Francisco, CA
- historical research San Francisco, CA
- research pharmacist San Francisco, CA