Founding AI Researcher, RL

Goaly; Palo Alto (CA); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Complimentary meals

Visa sponsorship

Job summary

Goaly, a stealth AI startup, seeks a research-engineering candidate to own the experimental loop turning a base model into a useful agent. You will design tasks, prepare data, run RL and post-training experiments, diagnose model behavior, and translate results into improved production models.

This role blends research and engineering, requiring coding proficiency, training-pipeline operations, and collaboration with RL systems, training, inference, product, and domain experts to accelerate

Qualifications

• Strong Python and software-engineering skills to turn research ideas into reliable experimental systems.
• Hands‑on experience training or evaluating modern language models, or related ML research area.
• Solid understanding of deep learning and optimization with RL intuition.

Responsibilities

• Design and run post-training experiments for agentic capabilities, including tool use, coding, reasoning, planning, long-horizon tasks, and recovery from failure.
• Prepare high-quality training and evaluation data: define task distributions, curate/filter examples, control contamination, balance difficulty, and build reproducible data-generation pipelines.
• Build realistic RL environments and task harnesses with clear interfaces, reliable resets, isolated execution, telemetry, and robust reward signals.
• Develop evaluations that measure capability and reliability; create regression suites, behavioral slices, error taxonomies, and dashboards linking metrics to model failures.
• Iterate on training recipes: supervised warm starts, sampling strategies, reward design, verifiers, curricula, optimization, and reinforcement fine-tuning methods.
• Analyze trajectories and model behavior to identify reward hacking, shortcut learning, mode collapse, distribution gaps, and other failure modes; turn findings into experiments.
• Improve research workflow via better experiment configuration, rollout inspection, reproducibility, checkpoint evaluation, and automated comparison of runs.
• Partner with systems engineers to debug cross-layer problems in rollout inference, environment execution, distributed training, and data movement.
• Translate successful research ideas into stable pipelines and shape the team's post-training roadmap.

Skills

Python

Reinforcement learning

Research engineering

Experimentation

Collaboration

Tools

PyTorch

JAX

DeepSpeed

Megatron

Ray

VeRL

Job description

About us

We’re building toward a world where every company can become its own AI lab.
Goaly is a stealth AI startup founded by ex-Meta MSL engineers and researchers. Our mission is to dramatically lower the cost, time, and talent barriers to building proprietary AI — and make each generation of models faster and cheaper to build than the last.

Backed by leading AI investors and endorsed by frontier AI researchers and builders, we’re looking for exceptional new grads who want to work on hard, foundational AI systems problems with outsized ownership from day one.

About the role

You will own the experimental loop that turns a capable base model into a useful agent. You will design tasks and environments, prepare training and evaluation data, run reinforcement-learning and related post-training experiments, diagnose model behavior, and convert results into better recipes and production models.

This is a research-engineering role. The best candidates are equally comfortable forming hypotheses, writing high-quality code, operating training pipelines, and investigating why a model or metric moved. You will work closely with RL systems, training, inference, product, and domain experts; when infrastructure slows the science, you will help improve the infrastructure rather than treating it as someone else’s problem.

What you'll do

• Design and run post-training experiments for agentic capabilities, including tool use, coding, reasoning, planning, long-horizon task completion, and recovery from failure.

• Prepare high-quality training and evaluation data: define task distributions, curate and filter examples, control contamination, balance difficulty, and build reproducible data-generation pipelines.

• Build realistic RL environments and task harnesses with clear interfaces, reliable resets, isolated execution, useful telemetry, and reward signals that are hard to game.

• Develop evaluations that measure both capability and reliability. Create regression suites, behavioral slices, error taxonomies, and dashboards that connect aggregate metrics to concrete model failures.

• Iterate on training recipes, including supervised warm starts, sampling strategies, reward design, verifiers, curricula, optimization choices, and reinforcement fine-tuning methods.

• Analyze trajectories and model behavior to find reward hacking, shortcut learning, mode collapse, distribution gaps, and other failure modes; turn those findings into targeted experiments.

• Improve the research workflow through better experiment configuration, rollout inspection, reproducibility, checkpoint evaluation, and automated comparison of runs.

• Partner with systems engineers to debug cross-layer problems in rollout inference, environment execution, distributed training, and data movement.

• Translate successful research ideas into stable, repeatable pipelines and help set the team's longer-term post-training roadmap.

You may be a good fit if you have

• Strong Python and software-engineering skills, including the ability to turn ambiguous research ideas into reliable experimental systems.

• Hands‑on experience training, fine‑tuning, or evaluating modern language models, or an exceptional record in a closely related ML research area.

• Solid understanding of deep learning and optimization, plus enough reinforcement-learning intuition to reason about policies, rewards, sampling, credit assignment, and evaluation bias.

• Excellent experimental judgment: you define controls, inspect data, validate metrics, keep results reproducible, and distinguish a real improvement from noise or leakage.

• Ability to debug across model behavior, data, code, and distributed infrastructure without losing sight of the user-facing capability being improved.

• Clear written and verbal communication and a track record of productive collaboration across research and engineering.

Strong pluses

• Experience with RLHF, reinforcement fine‑tuning, preference optimization, reward or verifier modeling, or large‑scale online sampling.

• Experience building agent environments, secure sandboxes, coding benchmarks, tool‑use tasks, or long‑horizon evaluations.

• Familiarity with PyTorch or JAX and distributed ML systems; experience with frameworks such as FSDP, Megatron, DeepSpeed, Ray, VeRL, or related stacks.

• A record of influential research, open-source contributions, technically ambitious independent projects, or production model launches.

How we work

• Mission first. We choose work for its impact on the mission and take responsibility for the outcome, not just our assigned tasks.

• High agency. We identify what is missing, form a plan, and move without waiting for perfect clarity.

• Speed with rigor. We ship, measure, and iterate quickly while protecting correctness, safety, and reliability.

• Flexible scope. We cross team and technical boundaries when that is the fastest way to solve the real problem.

• Low ego, high standards. We give direct feedback, change our minds when the evidence changes, and help the whole team win.

• Continuous learning. The stack changes quickly; we are willing to learn unfamiliar systems, methods, and domains as the work demands.

Location, visa sponsorship & benefits

• Hybrid in Palo Alto: 4+ days/week in office.

• Visa sponsorship: H-1B and OPT/CPT support available, with immigration counsel.

• Meals & perks: Complimentary lunch, dinner, snacks, and drinks.

A note on qualifications. We value exceptional ability over perfect keyword matches. If the work excites you and you can show strong technical ability, learning speed, or ownership, we encourage you to apply.

Equal opportunity

We are an equal opportunity employer. We consider qualified applicants without regard to race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, disability, veteran status, genetic information, or any other characteristic protected by applicable law. We provide reasonable accommodations for candidates who need them during the hiring process.