ZipRecruiter

Log In

1

Online Rlhf Jobs (NOW HIRING)

Zillow

Principal Applied Scientist, Agentic AI

$181K - $290K/yr

... RLHF, RLAIF, or DPO for multi-objective optimization. * Develop reward models and objective ... online and batch adaptation loops with strong guardrails. * Translate conversational logs ...

Amazon

Applied Scientist, Core Search

Seattle, WA

Apply Reinforcement Learning (RLVR, RLHF), Direct Preference Optimization (DPO), and customer ... well as online experiments. About the team Core Search builds the next-generation LLM-powered ...

Amazon

Applied Scientist, Core Search

Seattle, WA · On-site

Apply Reinforcement Learning (RLVR, RLHF), Direct Preference Optimization (DPO), and customer ... well as online experiments. About the team Core Search builds the next-generation LLM-powered ...

Hop

Senior AI Engineer

Los Angeles, CA

$112K - $154K/yr

End-to-End ML Lifecycle:  Own requirements → data prep → feature engineering → classical ML or LLM fine-tuning (LoRA, PEFT, RLHF) → offline/online evaluation → MLflow registry, with ...

previous pagenext page

Showing results 21-40

All JobsOnline Rlhf Jobs

Online Rlhf information

See salary details

$17.5K

$40.6K

$86K

How much do online rlhf jobs pay per year?

As of Aug 22, 2026, the average yearly pay for online rlhf in the United States is $40,596.00, according to ZipRecruiter salary data. Most workers in this role earn between $25,000.00 and $43,500.00 per year, depending on experience, location, and employer.

What is an online RLHF?

Online RLHF (Reinforcement Learning from Human Feedback) jobs typically involve helping to train AI models by providing human feedback on their outputs. Workers in these roles might review model responses, rate the quality of generated text, or suggest improvements to help the AI learn to produce better results. These jobs are often remote and can be done part-time or as contract work. They play a crucial role in improving the safety, usefulness, and accuracy of AI systems by aligning them more closely with human preferences.

What are some common challenges faced by online RLHF specialists when collaborating with cross-functional teams?

Online RLHF specialists often work closely with machine learning engineers, data annotators, and product managers. A common challenge is ensuring that feedback from human annotators is accurately integrated into model training, which requires clear communication and well-defined annotation guidelines. Additionally, balancing the pace of model updates with the need for high-quality human feedback can be demanding. Effective collaboration and regular syncs are essential to maintain alignment and achieve project goals.

What are the key skills and qualifications needed to thrive as an online RLHF specialist, and why are they important?

To thrive as an Online RLHF Specialist, you need a strong background in machine learning, reinforcement learning, and data analysis, typically supported by a degree in computer science or a related field. Familiarity with technical tools like Python, PyTorch or TensorFlow, and experience with human feedback systems or annotation platforms are highly valuable. Strong problem-solving, attention to detail, and the ability to communicate complex concepts clearly are crucial soft skills. These qualifications ensure the effective training and evaluation of AI models, leading to more accurate and reliable machine learning systems.

What is the difference between Online Rlhf vs Online Rlhf?

AspectOnline RlhfOnline Rlhf
CredentialsTypically requires certification in online health coaching or related fieldsTypically requires certification in online health coaching or related fields
Work EnvironmentRemote, online platform-basedRemote, online platform-based
Industry UsageCommon in health and wellness sectorsCommon in health and wellness sectors
Job FocusProviding health guidance and support onlineProviding health guidance and support online

Online Rlhf and Online Rlhf are the same role, often used interchangeably. Both involve providing health and wellness support remotely, requiring similar certifications and working within the online health industry. The key difference is often in terminology rather than job function.

More about Online Rlhf jobs

What cities are hiring for Online Rlhf jobs?

Cities with the most Online Rlhf job openings:

What are the most commonly searched types of Rlhf jobs?

The most popular types of Rlhf jobs are:

What states have the most Online Rlhf jobs?

States with the most job openings for Online Rlhf jobs include:

What job categories do people searching Online Rlhf jobs look for?

The top searched job categories for Online Rlhf jobs are:

Online Rlhf jobs near you
Infographic showing various Online Rlhf job openings in the United States as of August 2026, with employment types broken down into 61% Full Time, 36% Part Time, 1% Temporary, and 2% Contract. Highlights an 80% Physical, 1% Hybrid, and 19% Remote job distribution, with an average salary of $40,596 per year, or $19.5 per hour.

Member of Technical Staff - RL Research (Experienced)

Nuance Labs

Seattle, WA • On-site

Full-time

Medical, Retirement, PTO

Re-posted 17 days ago

Job description

About Nuance Labs
Nuance Labs is building photorealistic, real-time AI avatars with emotional intelligence: a full-duplex audiovisual system that can listen, speak, react, interrupt, and respond like a real person.
We're a research company, with PhDs from MIT, UW, Oxford, CMU, and Johns Hopkins, and industry experience from Apple, Meta, Amazon AGI, and more. The team is small, the work is real, and the problems are unsolved.
How Nuance Differentiates
Most conversational AI avatars today are hacks - a face slapped on a speech-to-speech pipeline, stuck in the uncanny valley: emotionless, mechanical, one-turn-at-a-time. Current systems take 2-5 seconds to respond; natural conversation requires sub-500ms. That's a 10x improvement, and it demands rethinking the entire stack.
That rethinking starts with full-duplex: an AI that listens and speaks simultaneously, perceives emotion in real time, and responds with a face that actually reflects it. It's an extremely hard problem, and we're developing foundation models designed for it from the ground up.
About the Role
We're looking for a deeply technical Member of Technical Staff to own RL and post-training for large-scale omni models. This posting is aimed at experienced researchers and engineers who've operated at a senior to senior-staff level at big tech or a leading research lab. Everyone at Nuance is MTS - we don't run title ladders - but we're hiring people who have already done this work at scale.
This role is broader than a traditional RL algorithm role. You will be expected to understand modern post-training methods and build the infrastructure needed to run them at scale. The work spans RL method development, rollout generation, reward modeling, policy optimization, evaluation, data feedback loops, serving, observability, and distributed execution.
You will build Nuance's RL/post-training stack from 0→1 and scale it from 1→10. That means turning rapidly evolving research ideas into reliable training systems: defining the abstractions, choosing or modifying frameworks, wiring together rollout workers and trainers, building reward/evaluation loops, debugging failure modes, and making the system fast enough for researchers to iterate.
For Nuance, post-training is not limited to text. Our models are omni from the ground up: audio, video, language, and real-time full-duplex interaction. We need RL and post-training methods that improve interactive behavior, timing, interruption, emotional response, audiovisual coherence, and real-time conversational quality.
This is a high-ownership role with direct impact on how Nuance models improve after pretraining.
What You'll Own
  • Build Nuance's RL/post-training stack from 0→1: rollout generation, policy optimization, reward/reference model serving, data feedback loops, evaluation, checkpointing, observability, and debugging.
  • Develop and scale post-training methods such as PPO, GRPO, DPO, rejection sampling, RLHF/RLAIF, online RL, and model-based data improvement.
  • Design the systems abstractions that connect research ideas to production-scale RL runs: trainers, rollout workers, reward models, evaluators, data queues, experience buffers, and checkpoint promotion.
  • Build evaluation and feedback loops for omni behavior: turn-taking, interruption, timing, emotional response, audiovisual coherence, instruction following, and real-time interaction quality.
  • Optimize the end-to-end post-training loop across rollout throughput, serving latency, GPU utilization, policy update efficiency, queueing, checkpoint overhead, and research iteration speed.
  • Evolve the platform as algorithms, model architectures, reward definitions, data sources, and evaluation methods change.
What We're Looking For
  • Significant hands-on experience with RL, RLHF, RLAIF, post-training, alignment, or large-scale fine-tuning for modern foundation models.
  • Deep understanding of RL/post-training methods: policy optimization, reward modeling, preference optimization, rejection sampling, KL control, evaluation, and data feedback loops.
  • A track record reasoning about model behavior and training dynamics: reward hacking, unstable rewards, distribution shift, stale policies, mode collapse, over-optimization, noisy preferences, and evaluation mismatch.
  • Proven experience building or operating RL/post-training pipelines at scale with frameworks such as verl, ms-swift, OpenRLHF, or equivalent internal systems, including integration with rollout serving systems such as vLLM.
  • Experience with large-scale training or inference systems, including rollout generation, model serving, batching, queueing, GPU utilization, checkpointing, and debugging.
  • Understanding of omni post-training for real-time audio-video-language interaction: temporal alignment, interruption, emotional response, and multimodal evaluation.
  • Strong software engineering fundamentals, curiosity, and adaptability to new RL algorithms, model architectures, serving systems, evaluation methods, and research ideas.
Bonus Points
  • Prior 0→1 experience building post-training systems, RL pipelines, agent training systems, evaluation platforms, or large-scale model improvement loops.
  • Experience with PPO, GRPO, DPO, online RL, RLHF/RLAIF, reward modeling, preference data, synthetic data generation, or model-based data improvement.
  • Experience with omni or multimodal post-training for audio-video-language models, especially long-context or real-time interactive systems.
  • Experience scaling mixed training/inference workloads across large GPU clusters.
  • Experience with adjacent areas such as distributed pretraining, data infrastructure, inference serving, simulation, human/AI feedback collection, or evaluation infrastructure.
  • Publications or substantial open-source contributions in RL, post-training, alignment, evaluation, ML systems, or model behavior.
Compensation
$300,000 - $500,000 base salary, plus meaningful equity. We think long-term ownership matters and structure equity accordingly.
Logistics
  • Location: In-person in Seattle, five days a week - we believe in the compounding value of working shoulder-to-shoulder.
  • Visa sponsorship: We sponsor visas (O-1, H-1B, green card, etc.) from day one.
  • AI-native tooling: Do your best work with the best tools, including unlimited tokens.
Benefits
  • Health: HSA plan with ~$2,000 in annual company contributions - roughly 2x what most big tech companies put in.
  • Time off: 15 days of PTO plus public holidays, and we close the office for a full week at year-end.
  • Food: Lunch, drinks, and snacks on us every workday - the small thing that quietly makes the day better.
  • Commuter benefits: We help cover the cost of getting to the office.
  • 401(k)

Nuance Labs is an equal opportunity employer. We believe diverse teams build better AI.

Apply