Ndea (YC W26) is hiring a symbolic RL search guidance lead
Source: Hacker News
Location
Remote
Type
Full-time
About Ndea
Ndea is building AGI systems that depend on search guidance. We’re hiring hands‑on researchers/engineers to drive our deep learning effort in search guidance, training models to make structured search more efficient and reliable.
This is a high‑ownership role for someone who wants to operate at the leading edge of neuro‑symbolic AI, designing, implementing, and validating new approaches in code.
We offer
- Meaningful equity, competitive salary, and benefits
- Aggressive compute budget
- Small, high‑talent‑density, globally remote team
Ndea is an equal‑opportunity employer and does not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability or any other legally protected status.
Apply
If you’re interested in this role, send an email to future@ndea.com with the following items:
- Your location (city, country)
- Something impressive you’ve created or published, ideally in the reinforcement learning or search guidance space
- Any experience/training you have in symbolic systems, logic programming, formal methods, or discrete math
- Links to your profile(s) (e.g., Google Scholar, GitHub, X, LinkedIn, etc.)
- Your resume (optional if the above links are sufficient)
Refer
Know someone who might be a good fit? Refer them to us, and if they’re hired and stay for 30 days, you could earn a $10,000 bonus.
Qualifications
- Strong hands‑on experience building and debugging RL or search‑driven learning systems
- Research contributions in reinforcement learning, planning, or search (papers and/or industry work)
- Evidence of turning research ideas into working implementations
- Comfort operating as an individual contributor in a small, high‑agency environment
- Interest in symbolic approaches (program synthesis, logic, solvers, formal methods, etc.)
- Clear communication and documentation skills for complex research/engineering workflows
Nice‑to‑have
- Experience with search‑guided learning in structured or combinatorial domains
- Work in planning‑heavy, exploration‑heavy, or solver‑adjacent settings
- Familiarity with discrete mathematics, verification, or theorem‑proving style problems
This role may not be a fit if you’re primarily focused on…
- LLM‑only RLHF or post‑training pipelines
- World model scaling or agent abstraction layers as the main artifact