# Rust edge guards and Wasm inference

Rust work targets Wasm edge guards, Candle or llama.cpp bindings, and deterministic benches where Python GIL or GC pauses break SLOs. We reproduce UTF-8 PDF failures and quant drift in isolated harnesses before production traffic. €2,400 24h PoC validates inference paths; €3,900 40h Prototype ships a callable API or sidecar; €3,100 Eval CI encodes groundedness and refusal gates in CI. Hardening €5,600 covers backpressure and crash isolation; MVP €8,500 adds tenant auth; audits from €8,000. No certification claims, only measured gates and handoff repos.

**Sprints from €2,400 PoC · €3,100 eval CI · €3,900 prototype · €5,600 hardening · €8,500 MVP · audit from €8,000** · Topic: `engineering-rust` · [Open proof](/#open-proof) · [Sample scorecard](/sample)

HTML: [/engineering/rust](/engineering/rust) · Markdown: [/engineering/rust.md](/engineering/rust.md)


_Rust edge and Wasm guards_

## Why teams trust this stack with Arviser

- Stack-specific gates for Rust edge guards and Wasm inference, not generic AI slideware.
- Senior engineers (10+ yrs) with daily eval tooling; founder architecture review (30+ yrs IT).
- Proof links include Open proof and sample scorecards, commercial sprints stay fixed-scope.

## Dual path

### For CTO / Staff Eng

Senior engineers (10+ yrs) build the vertical slice, wire retrieval and tools, and leave a repo your team can extend, with modular prompts, typed tool schemas, and CI eval fixtures.

### For VP Product / CFO

Fixed-hour packages (€2,400–€8,500) de-risk AI spend: kill fees on Risk-Shared PoC when narrow hypotheses fail, 100% PoC credit toward MVP on Go, and no surprise T&M overruns inside written scope.

Route: 24h PoC (€2,400) if unknown feasibility, else 40h Prototype (€3,900); add 32h Eval CI (€3,100) before scale; harden at €5,600 or ship MVP at €8,500.

## Stack-specific failure modes we gate in eval CI

- Wasm32 guard module panics on UTF-8 edge bytes in PDF streams, taking down the whole worker thread.
- Candle batching misaligns token masks when prompt templates mix Polish and English headings.
- Tokio spawn_blocking saturation hides latency spikes that only appear under concurrent SSE clients.

### Sample eval fragment (rust)

```
[eval.rust_edge]
model = "llama3-8b-q4"
cases = 40
pass_if = { groundedness = 0.86, refusal_rate = 0.12, p95_ms = 900 }
```

## Which sprint fits?

| Situation | Recommendation | Sprint |
| --- | --- | --- |
| Hard unknown on this stack | 24h Technical PoC | €2,400 · 3–5 days |
| Working demo, no CI evals | 32h Eval CI harness | €3,100 · 1 week |
| Pilot traffic soon | 60h Hardening or 80h MVP | €5,600–€8,500 |

## FAQ

### Do you build Rust edge guards and Wasm inference under fixed scope?

Yes. We deliver written scope in 48h and fixed-hour packages; overruns inside agreed spec are on us.

### Can we start with eval CI only?

Yes, 32h Eval CI from €3,100 when a prototype exists but gates do not.

Reviewed by Vadim Nareyko, 30+ yrs IT · Last updated 2026-11-06

## Related

[Engineering hub](/engineering) · [Open proof](/#open-proof)

