Research Engineer, Post-Training

cognition; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Doist is seeking an accomplished ML engineer to join Devin's post-training and alignment efforts. This role blends research and hands-on engineering to shape how ambitious AI agents learn, evaluate, and interact with humans in long-horizon tasks.

You will develop post-training recipes, design meaningful evaluations, and advance techniques like RLHF, RLAIF, and constitutional approaches. The team values rigorous experimentation, systems thinking, and rapid iteration in a world-class AI lab

Qualifications

• Post-training experience in ML systems and alignment
• Ability to design and run end-to-end evaluation pipelines
• Experience with large-scale distributed training is a plus
• Strong fundamentals in probability, statistics, and ML theory
• Ability to interpret experimental data and distinguish signals from noise

Responsibilities

• Develop post-training recipes across datasets, training stages, and hyperparameters.
• Design evaluations that capture meaningful signals and progress.
• Investigate results and diagnose why training behaves unexpectedly.
• Apply RLHF, RLAIF, and constitutional methods to agent behavior.
• Scale experiments with data and compute, exploring new methodologies.

Skills

RLHF

RLAIF

Reward learning

Probability

Statistics

ML theory

Job description

We are an applied AI lab building end-to-end software agents. We're the makers of Devin, the first AI software engineer. Our team is extremely talent-dense. Among our founding team, we have world-class competitive programmers, former founders, and leaders from companies at the cutting edge of AI including Scale AI, Palantir, Cursor, Waymo, Tesla, Lunchclub, Modal, Google DeepMind, and Nuro.Building Devin is just the first step—our hardest challenges still lie ahead. If you’re excited to solve some of the world’s biggest problems and build AI that can reason on real-world tasks.

Role Mission

Post-training is the critical bridge between raw model capability and a system that is actually useful, safe, and effective in the real world. You will shape how our agents learn by iterating on training recipes, evaluations, and alignment methods that directly determine what Devin and our future systems can do. This role blends deep research and hands‑on engineering. We don't distinguish between the two.

What You'll Accomplish

• Post-Training Recipe Development: Iterate on the full stack of datasets, training stages, and hyperparameters that determine model behavior. Measure how choices compound across evals and production performance, not just isolated benchmarks.
• Evaluation Design and Integrity: Build evals that actually capture what matters. The loop never ends: define, optimize, realize the gaps, and rebuild. You'll be responsible for making numbers go up and making sure the numbers mean something.
• Deep Understanding: When training produces results that don't make sense, you dig until you understand why. The goal isn't just to fix it; it's to carry that understanding forward to the next problem.
• Alignment and Agent Behavior: Apply and advance techniques like RLHF, RLAIF, and constitutional approaches to shape how agents reason, act, and collaborate with humans in long-horizon tasks.
• Scaling and Exploration: Measure how performance scales with data and compute, and develop new methodologies when existing ones hit ceilings. We expect both rigor and invention.

Exceptional Candidates Have Demonstrated

• A track record of advancing ML systems through post-training, alignment, or related methods: RLHF, RLAIF, preference modeling, reward learning, or equivalent.
• Strong fundamentals in probability, statistics, and ML theory. The ability to look at experimental data and distinguish real effects from noise and bugs.
• Evidence of original contributions: publications at top venues, open-source impact, or equivalent industry results.
• Experience with large-scale distributed training and the debugging that comes with it.
• Systems‑level thinking: not just model optimization, but understanding how training pipelines, data, and evaluation interact.
• Comfort with ambiguity and fast‑moving research environments where priorities shift quickly.

Resources & Environment

Small, highly selective team where research and product move together; prototypes reach real deployment quickly Compute is not a constraint: large allocations with training jobs routinely running across thousands of GPUs from day oneThe environment rewards speed, autonomy, and technical depth with minimal process overhead; this is one of the most competitive and fast‑moving problems in AI Everything needed to operate at frontier scale from day one.

Equal Opportunity

Cognition is an equal opportunity employer. We do not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other protected characteristic under applicable law. We are committed to providing reasonable accommodations for candidates with disabilities throughout the hiring process - please let us know if you need any.