Remote Agentic RL Researcher, Post-Training for Speech AI

DeepRec.ai

San Francisco (CA)

Hybrid

USD 225,000 - 275,000

Full time

11 days ago

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Healthcare
Dental
Vision

Job summary

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.

Qualifications

  • 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.

Responsibilities

  • 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.

Skills

Reinforcement learning
RL pipeline scaling
Chatbot/conversational agents
Experiment design

Tools

PPO
GRPO
DPO

Job description

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.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Machine Learning Researcher, Agentic RL
Machine Learning Researcher, Agentic RL

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)

On-site
USD 170,000 - 230,000
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
Applied RL Researcher - Post-Training & Evaluation
Applied RL Researcher - Post-Training & Evaluation

Confidential • New York (NY)

Hybrid
USD 120,000 - 180,000
Remote RL Post-Training Scientist for Decentralized AI
Remote RL Post-Training Scientist for Decentralized AI

Pluralis Research • California

Remote
USD 150,000 - 230,000
Equity-heavy package
Remote-first culture
Visa sponsorship
+1
Remote LLM Research Scientist - Pre/Post-Training
Remote LLM Research Scientist - Pre/Post-Training

Synthires • California

Remote
USD 138,000 - 165,000
Weekly payments
TTS Research-to-Production Lead (Remote/Hybrid)
TTS Research-to-Production Lead (Remote/Hybrid)

DeepRec.ai • San Francisco (CA)

Hybrid
USD 270,000 - 330,000
Healthcare
Equity
Director, Speech AI Research — Remote ASR Leader
Director, Speech AI Research — Remote ASR Leader

Recruits Lab • United States

Remote
USD 315,000 - 385,000
Sign-on bonus may be available.
Remote work
Agentic Coding Research Scientist
Agentic Coding Research Scientist

Bison • San Francisco (CA)

On-site
USD 400,000 - 500,000
Health, dental, and vision benefits
Unlimited PTO
Paid parental leave
+1
Senior AI Engineer (Remote) — RLHF & Model Alignment
Senior AI Engineer (Remote) — RLHF & Model Alignment

prolificacademicltd • United States

Remote
USD 83,000 - 110,000
Remote engagement
Flexible hours
Short skills assessment