Machine Learning Researcher, Agentic RL

DeepRec.ai

San Francisco (CA)

Hybrid

USD 225.000 - 275.000

Vollzeit

Vor 11 Tagen

Eine vollständige Bewerbung in einer Minute

Maßgeschneiderter Lebenslauf und Anschreiben – versandbereit.

Schaffe es an den ATS-Filtern vorbei

Benefits dieser Stelle

Healthcare
Dental
Vision

Zusammenfassung

DeepRec.ai in San Francisco is seeking an Agentic RL researcher to own post-training for the next text-to-speech model. You will design and run RL loops (PPO/GRPO/DPO) and build scalable, self-curating data pipelines that generate training signals for reinforcement learning.

You will collaborate with speech researchers to ensure that improvements in text lead to better audio performance. The role is full-time, with hybrid SF or remote work and start date ASAP.

Qualifikationen

  • Hands-on RL or preference learning with measurable behavioural changes.
  • Built or led a scalable RL pipeline that generates its own questions/tasks.
  • Experience at a real company with chatbot-style or conversational agents.
  • Bonus: audio/speech post-training, large-scale training, published work.

Aufgaben

  • Own RL post-training for the next text-to-speech model.
  • Design and run PPO, GRPO, DPO or on-policy loops on model weights.
  • Build pipelines that write their own questions and tasks for scaling.
  • Coordinate with speech researchers to transfer text improvements to audio.

Kenntnisse

Reinforcement learning
RL pipeline scaling
Chatbot/conversational agents
Experiment design

Tools

PPO
GRPO
DPO

Jobbeschreibung

Agentic RL researcher, post-training (San Francisco or remote)
About the company

A well-funded voice AI company in San Francisco, building speech models after a recent raise. The research team is growing, with several researcher roles open at once, and is kept deliberately flat. This role reports to the Head of AI.

The role

You’ll own the RL side of post-training the next text-to-speech model. A big part of how that model gets good is how it’s post-trained, which means building complex, text-based agent loop systems that generate the training signal for RL. You’ll design and run PPO, GRPO, DPO or on-policy loops on model weights, with the environments and rewards that go with them. You’ll also build pipelines that write their own questions and tasks, so training scales without constant manual data curation. Ablations show what moved behaviour, and you’ll work with the speech researchers so what you build in text carries over to audio.

What we’re looking for
  • Hands-on RL or preference learning that trained model weights and changed behaviour in a way you can measure.
  • You’ve built or led an RL pipeline that scales, ideally one that generates its own questions and tasks (curating an SFT dataset on its own isn’t what this role needs).
  • You’ve done it at a real company, with real constraints, on chatbot-style or conversational agents.
  • Bonus: audio or speech post-training, large-scale distributed training, and published or open-source work in LLM post-training.
Salary and benefits

Up to around $250k depending on experience, plus equity. Healthcare, dental and vision.

Logistics

Full-time, permanent. San Francisco hybrid or fully remote. Start date ASAP.

Hol dir deinen kostenlosen, vertraulichen Lebenslauf-Check.

oder ziehe deine Datei hierhin.

Similar jobs

Ähnliche Jobs, die dir auch gefallen könnten

Remote Agentic RL Researcher, Post-Training for Speech AI
Remote Agentic RL Researcher, Post-Training for Speech AI

DeepRec.ai • San Francisco (CA)

Hybrid
USD 225.000 - 275.000
Healthcare
Dental
Vision
Post-Training RL Researcher for Production AI
Post-Training RL Researcher for Production AI

present of AI • San Francisco (CA)

Vor Ort
USD 170.000 - 230.000
Machine Learning Engineer, Speech LLMs
Machine Learning Engineer, Speech LLMs

DeepRec.ai • San Francisco (CA)

Hybrid
USD 243.000 - 297.000
Performance bonus
Equity
Healthcare for you and dependents
+1
Member of Technical Staff - Research Engineer, Post-training
Member of Technical Staff - Research Engineer, Post-training

Preference Model • San Francisco (CA)

Vor Ort
USD 180.000 - 240.000
Competitive cash and equity (>90th pct
Ownership and autonomy
Lunch onsite
+4
Machine Learning Researcher, TTS
Machine Learning Researcher, TTS

DeepRec.ai • San Francisco (CA)

Hybrid
USD 270.000 - 330.000
Healthcare
Equity
Research Engineer: Post-Training & Agentic RL Platforms
Research Engineer: Post-Training & Agentic RL Platforms

Storm3 • San Francisco (CA)

Hybrid
USD 250.000 - 400.000
Relocation package
Competitive salary
Medical, dental, and vision insurance
Research Engineer
Research Engineer

Storm3 • San Francisco (CA)

Hybrid
USD 250.000 - 400.000
Relocation package
Competitive salary
Medical, dental, and vision insurance
Research / Data Engineer – Post-Training & RL
Research / Data Engineer – Post-Training & RL

Rnb Consultancy • San Francisco (CA)

Vor Ort
USD 250.000 - 300.000
Artificial Intelligence Researcher - Post Training
Artificial Intelligence Researcher - Post Training

Velocity Tech • San Francisco (CA)

Vor Ort
USD 120.000 - 180.000
Research Scientist - RL Training
Research Scientist - RL Training

snorkelai • USA

Remote
USD 200.000 - 350.000