Research Engineer — Agentic Systems

Compensation

USD 180,000-260,000 base · sabbatical accrual + a 800 H100-hour/quarter research-dividend equivalent (alphabell does not issue equity; see /funding for the rationale).

What you'll do

• Drive engineering for substrate v2 — the runtime layer that exposes persistent state, learned tool affordances, identity, and resource budgets as first-class primitives to substrate-hosted agents.
• Co-author cell-published reports and open-source releases (ab-circuits, ab-trace, ab-pairs) that put the substrate's safety machinery into the hands of external researchers.
• Carry a fair share of paired-interpretability operational work — artefact pipelines, disagreement-handling state machines, escalation channels — so that pairing functions as a real check rather than a ceremony.
• Run weekly compute requests through the federated scheduler, write the pre-registrations for any RSI-adjacent runs your cell takes on, and represent your cell at the cross-axis methodology review pool.
• Mentor cohort contributors rotating through fourier-67 / kalman-04 during the project-rotation phase of contributor onboarding.
• Contribute to the substrate's content-addressed execution-trace store (ab-trace v4 design is in active flight) and to the multi-agent negotiation primitives that kalman-04 is consolidating.
• Take seriously the lab's structural commitments: signed proposals, weighted-consensus governance, staged publication policy. Vote-of-record accrues at 24 months of signed contribution.

What we look for

Must-haves

• 5+ years of engineering experience at frontier scale — distributed training infrastructure, agent frameworks, or comparable production-grade ML systems.
• Demonstrated experience building or contributing substantively to agentic systems beyond prompt-only orchestration (persistent state, tool catalogues, multi-step execution).
• ML and RL fluency at the level where you can read frontier papers, reproduce results, and identify methodological weaknesses.
• Strong written communication. We publish to a common index and we expect contributors to write — your engineering work will be read by interpretability cells with no obligation to ask you nicely if a trace is confusing.
• Comfort with the lab's structural commitments: dual-use review, paired interpretability, pre-registered stopping conditions, staged publication. If any of those feel like obstacles rather than features, this is the wrong role for you.
• PhD in computer science, ML, or a closely related field — or equivalent industry experience demonstrated by published technical work.

Nice-to-haves

• Alignment Forum posts, LessWrong sequences, or comparable public writing on AI safety topics.
• Prior contributions to open-source oversight tooling (ab-circuits, transformer-lens, debate-based harnesses).
• Comfort with formal trace specifications, content-addressed storage, and the unglamorous side of substrate plumbing.
• Experience leading a small team or cell-equivalent of 3-7 researchers / engineers.
• Familiarity with Tel Aviv-region academic AI safety communities (Aviva Stern, Liora Sabatini, and Eitan Berkovich are anchored here).
• Reading proficiency in Hebrew is welcome but not required.

What we offer

• Relocation support — for roles that involve moving anchor or country, the lab covers reasonable relocation costs (movers, short-term accommodation up to 8 weeks, and a one-time settlement allowance). The standard relocation package is documented and rate-equalised; we do not negotiate it individually.
• Visa sponsorship — where the residency country and role warrant it, the lab sponsors work visas and (for long-tenured roles) supports the pathway to permanent residency. Visa work is shepherded by the relevant anchor steward, not outsourced to a third-party HR firm.
• Parental leave — 26 weeks fully paid for birthing parents, 16 weeks fully paid for non-birthing parents, with a phased return-to-work option. This is independent of country of residence and is one of the lab-wide compensation policies that is not negotiable.
• Sabbatical — every contributor accrues sabbatical time from year one; full-time contributors at the 36-month tenure mark are eligible for a 12-week paid sabbatical, with a longer 24-week option at 72 months. Sabbaticals are taken; we monitor.
• Compute allowance — every full-time research role carries an associated research-dividend H100-hour quarterly allowance, allocated through the federated scheduler under the standard mechanism. The allowance is in addition to your cell's pooled compute and is yours to direct.
• Conference and travel budget — USD 12,000-18,000 per year (role-dependent) for attendance at NeurIPS / ICLR / ICML / AAMAS / CAV / POPL / AISI workshops, plus an additional invited-talks allowance covered independently.
• Sustainable workload — explicitly anti-burnout — the lab tracks contributor working hours (self-reported, monthly) and treats sustained overage as a structural problem to be addressed at the cell-steward or anchor-steward level rather than a virtue to be celebrated. We have data on which cells push their members hardest and we act on it. Vote-of-record contributors have the standing to flag burnout patterns in their own or adjacent cells.
• Equipment — laptop of your choice, an ergonomic workstation, and a contributor allowance for the secondary equipment you'll inevitably need.

How to apply

Send your application to apply@alphabell.com. We respond to every application; we do not use applicant-tracking automation that ignores submissions.

Required:

• A CV or résumé covering your research and engineering trajectory, including specific roles and the substantive technical work in each.
• Two short pieces of public writing in the style of an Alignment Forum post or an alphabell internal-index report (800-1,500 words each). These should be on AI safety topics; we are looking for evidence of substantive thinking under conditions where the answer is not yet clear. If you have prior public writing that fits, send links instead of new writing.
• A 1-page research proposal scoped to the role you are applying for, naming the cell(s) you would want to work with and the specific question you would want to take on in the first 12 months. Proposals do not need to be definitive — we revise these together once we start talking — but they need to be concrete.

For PhD and postdoctoral roles, also include two references; we will reach out to them after the second interview round.

We typically respond within four weeks. Our interview process — for non-PhD roles — has three stages: a written exchange about the proposal, a 90-minute substantive conversation with the host cell, and a final meeting with the relevant axis steward. We do not whiteboard-code; we do not do leetcode-style interviews; we do not run timed take-home tests.

Equal opportunity

Equal opportunity statement. alphabell is committed to a contributor pool that is broad in background, country of residence, training history, and structural perspective. We do not discriminate on the basis of race, colour, national or ethnic origin, religion, sex, gender identity, sexual orientation, age, disability, veteran status, marital status, pregnancy or parenthood status, or any other protected characteristic under applicable law. We actively seek applicants from communities under-represented in AI safety research, and we treat the structural commitments described in our research conduct charter — including those bearing on dual-use research and paired interpretability — as applying equally to every contributor regardless of background. The lab's anchor stewards and the long-tenured contributor pool review hiring and onboarding patterns quarterly; substantive disparities are treated as governance items rather than as HR statistics. If you require accommodation in the application or interview process, please indicate this in your initial email; the request will be handled by the anchor steward responsible for the role rather than by an outsourced HR function.

---

Other open roles

← All open roles