Rlhf Jobs (NOW HIRING)

Experiment and prototype RLHF/RLAIF/RLVR/RM/DPOstyle training loops to improve real-world task and agent performance. * Land research in product: ship improvements into Labelbox workflows, services ...

Post-train LLM agents using RLHF, DPO, GRPO, PPO, and emerging methods * Build pipelines that convert human-labeled traces and verifiable signals into training data * Architect multi-turn, tool-using ...

You will use advanced techniques like prompt engineering, RLHF, and instruction tuning to ensure our models produce high-quality, context-aware responses. Responsibilities: * Lead the fine-tuning ...

Develop constitutional AI principles and assist with RLHF alignment pipelines. Qualifications: * Background in cybersecurity, prompt engineering, or adversarial ML. * Experience with jailbreak ...

... LoRA, RLHF, DPO, and model distillation techniques. • Implement model evaluation pipelines and benchmark reporting. • Collaborate with Prompt & Data teams to create repeatable model tuning ...

SFT data curation, preference data collection for RLHF/DPO, golden datasets, custom benchmarks, LLM-as-judge pipelines, human-in-the-loop evaluation, red teaming, and multimodal eval (text, image ...

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 ...

A core part of the role is post-training these models using RLHF, DPO, and related optimization techniques to push detection accuracy and false-positive rates beyond what off-the-shelf solutions can ...

Develop novel methods (e.g., mixture-of-experts/routing, DPO/RLHF, quantization, speculative decoding) and ship reference implementations. * Collaborate with engineering to transfer research into ...

Apply RLHF, ranking, and reward modeling techniques to improve response quality over time * Stay current with the latest generative AI developments and apply them to new use cases Qualifications

... RLHF, DPO, reward hacking mitigation); LLM-as-judge calibration, rubric design, and bias detection; intelligent evaluation strategies including active learning for test selection and automated ...

Design and evaluate techniques such as RLHF, DPO/GRPO, SFT, reward modeling, and preference optimization to improve instruction-following, controllability, and safety. * Develop efficient ...

A core part of the role is post-training these models using RLHF, DPO, and related optimization techniques to push detection accuracy and false-positive rates beyond what off-the-shelf solutions can ...

... RLHF, DPO, and PPO as mechanisms for aligning and improving agentic behaviors • Contribute to multi-agent systems where specialized agents collaborate, negotiate, and self-organize to solve ...

Finetune and extend existing models (LoRA, instruction tuning, RLHF) * Build and maintain data pipelines from product databases, documents, APIs, and logs * Ship reliable, monitored, production ...

Fine‑tune and extend existing models (LoRA, instruction tuning, RLHF) * Build and maintain data pipelines from product databases, documents, APIs, and logs * Ship reliable, monitored, production ...

Fine-tune and extend existing models (LoRA, instruction tuning, RLHF) * Build and maintain data pipelines from product databases, documents, APIs, and logs * Ship reliable, monitored, production ...

You will use advanced techniques like prompt engineering, RLHF, and instruction tuning to ensure our models produce high-quality, context-aware responses. Responsibilities: * Lead the fine-tuning ...

Supervised fine-tuning + preference/trace RL (DPO/RLAIF/RLHF), dataset curation, reward shaping, safety filters. Tech signals : - Has shipped agents that pass real repos' test suites end-to-end ...

You will use advanced techniques like prompt engineering, RLHF, and instruction tuning to ensure our models produce high-quality, context-aware responses. Responsibilities: * Lead the fine-tuning ...