Head of Reinforcement Learning / Post-Training

FOUND

West Hollywood (CA)

On-site

USD 220,000 - 360,000

Full time

4 days ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

FOUND, a founding leadership role with equity, seeks a Head of RL / Post-Training to help shape the company’s AI infrastructure for real-world data-to-training pipelines. You’ll own RL and post-training strategy, and directly influence the product and research direction with founders.

You will build and lead a world-class team of researchers and engineers, delivering scalable RL environments, training systems and evaluation benchmarks, partnering with frontier lab customers on outcomes.

Qualifications

  • Hands-on experience post-training LLMs or agents with RL at a frontier lab, top AI startup or leading research group.
  • Track record of shipping: models, RL environments, training systems or influential research.
  • Deep technical skill in Python, PyTorch and distributed training at scale.
  • Strong intuition for reward design, credit assignment and training stability.
  • Ability to move between research and production at startup speed.
  • Experience leading or mentoring technical teams, or a clear desire to build one.

Responsibilities

  • Set the RL and post-training strategy: what we train, how and why.
  • Turn real operational data into RL environments, reward signals and training pipelines for agents.
  • Lead post-training end to end: SFT, preference optimization (DPO and related methods), RLHF / RLAIF and online RL (PPO, GRPO and similar).
  • Design reward models and verifiers, and guard against reward hacking.
  • Build scalable training and rollout infrastructure for long-horizon, multi-step agent tasks.
  • Work closely with the Evals & Benchmarks team so measurement and training reinforce each other.
  • Partner directly with frontier lab customers on environments and training outcomes.
  • Hire and lead a world-class team of research scientists and engineers.

Job description

FOUND is partnering with a fast-growing AI infrastructure company to hire its founding Head of RL / Post-Training.

The company has generated 9 figures in revenue in its first 6 months and already works with the world’s top AI labs. It builds the infrastructure that turns real companies’ operational data into training environments for AI agents. This is a founding leadership role with real ownership, meaningful equity and a direct line to the founders.

What you’ll do
  • Set the RL and post-training strategy: what we train, how and why.
  • Turn real operational data into RL environments, reward signals and training pipelines for agents.
  • Lead post-training end to end: SFT, preference optimization (DPO and related methods), RLHF / RLAIF and online RL (PPO, GRPO and similar).
  • Design reward models and verifiers, and guard against reward hacking.
  • Build scalable training and rollout infrastructure for long-horizon, multi-step agent tasks.
  • Work closely with the Evals & Benchmarks team so measurement and training reinforce each other.
  • Partner directly with frontier lab customers on environments and training outcomes.
  • Hire and lead a world-class team of research scientists and engineers.
What we’re looking for
  • Hands-on experience post-training LLMs or agents with RL at a frontier lab, top AI startup or leading research group.
  • A track record of shipping: models, RL environments, training systems or influential research.
  • Deep technical skill in Python, PyTorch and distributed training at scale.
  • Strong intuition for reward design, credit assignment and training stability.
  • Ability to move between research and production at startup speed.
  • Experience leading or mentoring technical teams, or a clear desire to build one.
Nice to have
  • Publications or open-source work in RL, RLHF or agent training.
  • Experience building RL environments for coding, tool use or computer-use agents.
  • Existing relationships with frontier lab research teams.
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Founding Head of RL & Post-Training Strategy
Founding Head of RL & Post-Training Strategy

FOUND • West Hollywood (CA)

On-site
USD 220,000 - 360,000
Member of Technical Staff - Research Engineer, Post-training
Member of Technical Staff - Research Engineer, Post-training

Preference Model • San Francisco (CA)

On-site
USD 180,000 - 240,000
Competitive cash and equity (>90th pct
Ownership and autonomy
Lunch onsite
+4
RESEARCHER, POST-TRAINING
RESEARCHER, POST-TRAINING

Makermaker • San Francisco (CA)

On-site
USD 120,000 - 160,000
Research / Data Engineer – Post-Training & RL
Research / Data Engineer – Post-Training & RL

Rnb Consultancy • San Francisco (CA)

On-site
USD 250,000 - 300,000
Founding Research Engineer – RL Environments & Evals
Founding Research Engineer – RL Environments & Evals

Rnb Consultancy • San Francisco (CA)

On-site
USD 150,000 - 200,000
Base salary $150k–$200k
Equity 0.25–0.5%
Profit sharing up to 4% of project
+1
Artificial Intelligence Researcher - Post Training
Artificial Intelligence Researcher - Post Training

Velocity Tech • San Francisco (CA)

On-site
USD 120,000 - 180,000
Research Scientist / Engineer – Reinforcement Learning Infrastructure
Research Scientist / Engineer – Reinforcement Learning Infrastructure

lumaai • United States

Remote
USD 180,000 - 260,000
Founding Engineer – RL Environments & Data
Founding Engineer – RL Environments & Data

CGS • San Francisco (CA)

On-site
USD 150,000 - 230,000
Unlimited AI spend
Daily lunch provided
Equity—meaningful
Founding Research Engineer
Founding Research Engineer

Scion Staffing, Inc. • San Francisco (CA)

On-site
USD 150,000 - 200,000
Founding Engineering Opportunity
Cutting-Edge AI Work
Leadership Growth
Member of Technical Staff, Post-Training
Member of Technical Staff, Post-Training

Ricursive Intelligence • Palo Alto (CA)

On-site
USD 210,000 - 320,000