RLHF Jobs

Prime Intellect is developing an open superintelligence stack, providing infrastructure that AI labs typically build internally to ambitious AI teams. Their platform, Lab, integrates compute, environments, evaluations, secure sandboxes, high-performance training, and deployment for post-training at scale, covering SFT, RL, tool use, agent workflows, and continuous model improvement. They are focused on building open-source frontier AI models trained for long-horizon tasks and the platform their research team uses. The company has secured significant funding from prominent investors and AI leaders, and is seeking individuals passionate about building at the intersection of frontier research, infrastructure, and go-to-market strategy for a nascent category.

$150k - $300k

Snorkel AI is seeking Forward Deployed Researchers to partner with frontier AI labs on challenging data problems. This customer-facing role requires deep technical and research expertise to help design complex data and environments that enhance frontier model performance. You will act as a thought partner, working at the intersection of research, technical strategy, and customer collaboration. Your responsibilities will include scoping training data needs, designing RL environments, developing evaluation frameworks, analyzing model behavior, and translating customer objectives into technical plans.

$160k - $400k

Our Internal Acceleration team is building agents to accelerate the production of frontier tokens. You will work directly with founders and embed with our production team to create new agentic harnesses and operating systems, transforming hardware development in an AI-native world. Success is measured by how much faster the company moves, not just lines of code. This role is for engineers who thrive on ambiguity, possess strong product sense, and want to own problems end-to-end, acting as a launchpad for future founders. The problems are time-sensitive and business-critical, and the role demands dedication beyond a typical 9-5.

$150k - $400k

Cohere

Cohere is seeking a Member of Technical Staff to join our Post-Training Data Infrastructure team. In this role, you will be responsible for building and managing the critical data pipelines that generate post-training data for our large language models (LLMs). This includes data for SFT, preference, and RL post-training, as well as synthetic and human-annotated data. You will collaborate closely with researchers and annotation teams to ensure rapid iteration on data, enabling them to keep pace with model development. Your work will be instrumental in advancing the capabilities of our foundation AI models and delivering value to enterprise customers.

CA$295k - CA$535k

Cohere

Cohere is seeking a Member of Technical Staff to focus on post-training large language models (LLMs) using reinforcement learning and developing methods for improved generalization. This role involves designing training recipes, environments, and evaluations to ensure models learn skills effectively and generalize beyond their training data. You will collaborate with data infrastructure, evaluation, and pre-training teams to translate research findings into robust training procedures for production models. The ideal candidate is passionate about advancing AI capabilities and contributing to the widespread adoption of AI in enterprise solutions.

CA$295k - CA$535k

NVIDIA is seeking a Senior Engineer to lead the performance modeling, evaluation, and post-training of large language models focused on code generation and agentic coding tasks. This role involves optimizing model capabilities, efficiency, and reliability by working at the intersection of model training, inference, and empirical analysis. You will design experiments to understand model behavior, identify performance bottlenecks, and develop post-training strategies to achieve measurable improvements in coding benchmarks and real-world software engineering tasks. Collaboration with research scientists, infrastructure engineers, and product teams will be key to translating model insights into production-ready features.

$224k - $431k

We are seeking PhD research interns to advance the next generation of large language models using reinforcement learning. Our applied deep learning research team pioneers projects like Megatron, MT-NLG, and DLSS, building state-of-the-art foundation models and developing new methods to enhance their reasoning, alignment, reliability, and ability to solve real-world tasks. This internship will focus on algorithmic research at the intersection of reinforcement learning and large language models, involving the design, implementation, and evaluation of new RL-based methods for improving LLM behavior through hands-on experimentation and rapid prototyping at scale.

$0k - $0k

Luma is seeking a Research Scientist/Engineer to build the systems that enable reinforcement learning (RL) at a frontier scale. This role involves coupling policy optimization with large fleets of inference workers, agentic environments, and reward/verification systems to translate model behavior into learning signals. RL is crucial for Luma's models to evolve from capable to useful. This is a full-loop systems problem encompassing training, rollout generation, environment execution, and reward computation across thousands of GPUs, requiring speed, stability, and correctness. The ideal candidate has experience with post-training LLMs using RL, building environments and verifiers, and debugging large-scale asynchronous rollout pipelines.

HappyRobot is seeking a Product Engineer Intern to develop internal applications and AI agents that enhance operational efficiency across product, engineering, deployments, and go-to-market teams. This role involves building software that is actively used by the HappyRobot team, with guidance from experienced engineers. You will collaborate directly with the CTO and Head of Product, and your work will directly impact various departments by creating tools, agents, and data pipelines to automate workflows and improve processes.

Baseten powers mission-critical inference for leading AI companies by uniting applied AI research, flexible infrastructure, and seamless developer tooling. We enable companies at the frontier of AI to bring cutting-edge models into production. This role focuses on the applied end of post-training research, working directly with stakeholders from fast-growing AI companies to post-train open-source models that outperform frontier closed models on specialized tasks. The day-to-day involves extracting signal from complex, domain-specific datasets and building reward functions, environments, eval harnesses, and training pipelines to improve models that ship to production and reach millions of users.

$200k - $275k

Anthropic

Anthropic's Environments organization is responsible for building and maintaining the infrastructure that enhances Claude's capabilities through reinforcement learning. This includes developing frameworks for researchers to build environments and the underlying infrastructure for running them, with a core mission to productionize research. The role involves embedding with research teams to understand their workflows and designing frameworks and APIs that accelerate their progress, ensuring these systems are understandable, ownable, and maintainable. A significant part of the role also includes ensuring the health, maintainability, monitoring, and ease of triage for production RL runs. The ideal candidate will possess deep Python expertise, a strong sense of API and framework design, and an intuitive understanding of complex system failures, particularly silent ones. Experience with stateful distributed systems like workflow engines or actor frameworks is a plus. The role requires comfort in navigating and abstracting complex research codebases, incrementally improving them while research continues, and leveraging AI tools for development with a focus on verification.

$405k - $605k

NVIDIA is seeking Senior Deep Learning Scientists to advance their work in streaming and agentic multimodal AI. This role involves developing models capable of reasoning, planning, and acting across diverse modalities, with a focus on defining core algorithmic improvements for multimodal foundation models. You will contribute to high-impact, large language models and multimodal AI products that enhance user experiences, working within the Nemotron LLM team to solve real-world agentic AI challenges.

$184k - $288k

Mercor is seeking a Research Scientist Intern to contribute to cutting-edge research in AI. This role focuses on post-training techniques, reinforcement learning with verifiable rewards (RLVR), data generation, and model evaluation. You will investigate how different datasets, rewards, and training methods influence the capabilities and behavior of large language models. The internship involves designing experiments, developing new evaluation methodologies, analyzing model failures, and improving aspects like tool use, agentic behavior, and real-world reasoning. You will collaborate with researchers and domain experts, with the potential for your work to support publications and the development of advanced AI systems.

NVIDIA is seeking Senior Deep Learning Scientists to advance our work in streaming and agentic multimodal AI. This role involves developing models capable of reasoning, planning, and acting across diverse modalities, with a focus on defining core algorithmic improvements for multimodal foundation models. You will contribute to high-impact, large language models and multimodal AI products that enhance user experiences, working within our Nemotron LLM team.

$152k - $288k

NVIDIA is seeking Senior Deep Learning Scientists to advance our work in streaming and agentic multimodal AI. This role involves developing models capable of reasoning, planning, and acting across diverse modalities, contributing to core algorithmic improvements for multimodal foundation models. You will work on high-impact, large language models and multimodal AI products that enhance user experiences, joining our Nemotron LLM team to tackle real-world agentic AI challenges.

$184k - $288k

Anthropic

Reinforcement learning (RL) is crucial for Claude's ability to reason, write code, and act autonomously over long horizons. This role is part of the team responsible for building and maintaining the RL training system, which is used to train production models and for researchers across Anthropic to run their experiments. The team collaborates closely with research teams company-wide on the science and engineering required to scale RL effectively. As a Research Engineer, you will be at the heart of RL at Anthropic, with a direct view of RL training at the frontier, as the system you own supports both production and research runs. You will work with collaborators across research teams to understand system performance, identify areas of fragility, and drive future improvements.

$500k - $850k

Ema builds AI Employees for HR, IT, and Finance, automating busy work across the employee experience from recruiting and onboarding to IT support and payroll. Our team, comprised of engineers from top tech companies and graduates from prestigious universities, is backed by leading investors and operates at the forefront of Agentic AI in production. We are developing systems where AI agents learn and improve from their real-world tasks, creating a continuous loop of production data, training, evaluation, and enhanced agent performance. The core challenge lies in determining the most effective interventions to improve agent behavior in live workflows.

HUD is seeking a Product Engineer to transform significant product challenges into tangible user experiences across its AI data platform and marketplace. This role involves collaborating with product, design, engineering, research, and go-to-market teams to identify user pain points in AI data creation and training, define product improvements, and develop solutions. The position blends product strategy, interaction design, and full-stack development, requiring the ability to translate complex technical workflows into clear and user-friendly interfaces while retaining necessary detail.

$100k - $225k

Tennr is seeking a high-agency Senior Backend Engineer to connect advanced ML research with practical product delivery. You will architect and develop agentic workflows designed to tackle complex healthcare processes, addressing infrastructure, workflow, and user experience challenges within the U.S. healthcare system. This role involves constructing data pipelines, evaluation frameworks, and scalable, production-ready agentic systems. You will be tasked with identifying and implementing the most suitable tools and models for each specific workflow, ensuring optimal technology utilization.

$190k - $215k

Anthropic

Anthropic's production models undergo sophisticated post-training processes to enhance their capabilities, alignment, and safety. Decisions in production training depend on knowing how the model is really behaving. This role's mission is to have the best observability into production post-training runs at Anthropic, providing the clearest, most trusted view of model quality during training. You will shape what gets measured, keep the signal trustworthy and timely, and investigate surprising results to inform post-training and release decisions.

$500k - $850k