Member of Technical Staff, Heterogeneous Runtime & Placement

General Diffusion, Inc.; San Francisco, Northern (CA, KY); Hybrid; USD 170,000 - 250,000; Full time

Job summary

General Diffusion, Inc. seeks a Member of Technical Staff to own the execution contract for cross-target workloads. You will ensure visible, reversible runtime actions and rejects infeasible targets before ranking candidates.

Collaboration with compiler, GPU systems, and safety teams shapes capability and guardrail signals. You will design guarded rollout, canary, and rollback mechanisms, and document end-to-end traces from request through placement to outcome, enabling auditability and safe

Qualifications

• Experience shipping or operating a scheduler, inference-serving system, or distributed runtime.
• Judgment on heterogeneous workload lifecycles: compatibility, admission, failure and recovery.
• Ability to formalize constraints into explicit contracts and observable state transitions.

Responsibilities

• Define the execution contract mapping workload requirements to target capabilities and runtime checks.
• Build runtime and control-plane paths linking workloads to targets with safe fallback.
• Ensure decisions are inspectable by capturing eligibility, target, context, actions, and outcomes.
• Develop conformance tests and canary/recovery drills for partial failures feature guards.

Skills

Scheduler experience

Distributed systems

Telemetry & debugging

Guarried rollout design

Tools

Tracing systems

Canary tooling

Observability platforms

Job description

Member of Technical Staff, Heterogeneous Runtime & Placement

Own the execution contract for what runs where across different compute targets.

Status Open

Area Systems

General Diffusion is building compute world models and constrained planning so workloads can run across unlike, externally available compute targets. This role owns the production execution contract that turns an approved placement into a compatible, observable, and reversible runtime action - eliminating infeasible targets before ranking valid candidates - rather than training models, authoring kernels, or deciding the independent safety boundary.

01 / The work

What you'll work on

• Define the execution contract that maps workload requirements, target capabilities, runtime compatibility, and resource availability into explicit placement eligibility checks before any ranking occurs.
• Build the runtime and control-plane paths that bind approved workloads to supported targets, reconcile intended versus observed execution state, and preserve a safe fallback when a target cannot execute the work.
• Make each placement decision inspectable: capture the eligibility result, selected target, relevant runtime and workload context, fallback or re-placement action, and execution outcome.
• Implement bounded re-placement and reversal paths for failures, incompatibilities, or degraded execution; exercise those paths through canaries and recovery drills rather than relying on an untested rollback claim.
• Develop conformance and lifecycle tests across supported runtimes and target classes, including admission, launch, recovery, and cleanup behavior under partial failure.
• Partner with compiler, GPU systems, fleet, measurement, and safety teams to consume capability, cost, topology, and guardrail signals at clear interfaces; do not absorb their code-generation, physical-fleet, or authorization ownership.

02 / The background

What you bring

• Hands-on experience shipping or operating a scheduler, inference-serving system, distributed runtime, or control plane where a decision must be carried through to real execution.
• Practical judgment about heterogeneous workload lifecycles: device and runtime compatibility, resource admission, dependency or environment mismatches, partial failure, and recovery.
• Ability to turn ambiguous placement constraints into explicit contracts, test cases, and observable state transitions rather than opaque heuristics.
• Strong systems-debugging and telemetry skills, including tracing a decision from requested resources through binding, execution, and fallback.
• Experience designing guarded rollout, canary, and rollback mechanisms with an operational understanding of idempotency, reservations, and failure containment.

03 / The evidence

What progress looks like

• A reviewed execution contract and automated conformance matrix demonstrate that known-incompatible target/runtime combinations are rejected before ranking, while valid alternatives retain explicit eligibility evidence.
• Shadow or canary execution records provide an end-to-end trail for representative supported workloads—from request and placement rationale through observed binding and outcome—with failure and fallback states distinguishable in the data.
• A documented reversal drill demonstrates re-placement or rollback for selected compatibility and runtime-failure scenarios, with prior state, decision history, and the independent safety boundary preserved for audit.

04 / In the system

Where this role fits

Owns production decision execution, not model training or kernel authoring.