---
title: "Staff Agentic Runtime & Sandbox Engineer"
slug: "staff-agentic-runtime-sandbox-engineer"
id: "0e2ecffd-097e-4af1-b6f5-0a8f20a7cded"
department: "Applied AI"
department_code: "APP"
location: "Palo Alto, CA"
workplace_type: "On-site"
employment_type: "Full-time"
compensation: "$235k – $340k (annual package)"
is_remote: false
is_featured: false
headcount: 1
canonical_url: "https://jobs.talent247.co/jobs/staff-agentic-runtime-sandbox-engineer"
markdown_url: "https://jobs.talent247.co/jobs/staff-agentic-runtime-sandbox-engineer.md"
apply_endpoint: "https://jobs.talent247.co/api/public/jobs/staff-agentic-runtime-sandbox-engineer/apply"
schema_endpoint: "https://jobs.talent247.co/api/public/jobs/staff-agentic-runtime-sandbox-engineer/form-schema"
webmcp_tool: "apply_for_role"
updated_at: "2026-11-15T17:38:56.118Z"
content_signal: "search=yes, ai-input=yes, ai-train=no"
---

# Staff Agentic Runtime & Sandbox Engineer

## Position Telemetry

- **Reference:** `STAFF-AGENTIC-RUNT`
- **Practice / Sector:** Applied AI (`APP`)
- **Location:** Palo Alto, CA
- **Workplace Type:** On-site
- **Employment Type:** Full-time
- **Compensation:** $235k – $340k (annual package)
- **Canonical HTML URL:** https://jobs.talent247.co/jobs/staff-agentic-runtime-sandbox-engineer

## Role Dossier & Specification

THE CLIENT & MANDATE
Our client is an iconic AI-native developer platform scaling across San Francisco and Palo Alto, CA, evolving software engineering from interactive in-editor assistance to fleets of autonomous background coding agents that clone repositories, spin up full microservice stacks, verify UI changes in headless browsers, and submit review-ready pull requests in parallel.

They have partnered with Talent247 to appoint a Staff Agentic Runtime & Sandbox Engineer onsite in Palo Alto, CA. Architecting at the intersection of operating-system virtualization, distributed storage, and language-server tooling, the successful candidate will build the instant-clone microVM cloud where millions of autonomous coding agents execute safely every day.

KEY RESPONSIBILITIES
• Architect sub-second Copy-on-Write (CoW) Firecracker/KVM microVM snapshotting, memory restore, and content-addressable filesystem layers booting warm multi-gigabyte monorepo environments in <250ms.
• Build high-speed, low-overhead agent tool daemons in Rust and TypeScript exposing incremental LSP diagnostics, tree-sitter AST queries, fast ripgrep/vector indices, headless browser inspection, and PTY terminal multiplexing.
• Design hermetic network egress proxies, secret-injection brokers, and fine-grained syscall/filesystem isolation so untrusted agent-generated code can run Docker Compose, databases, and unit suites safely inside multi-tenant infrastructure.
• Engineer stateful session hibernation, live workspace syncing between cloud sandboxes and local developer machines, and deterministic trajectory replay for RL post-training.
• Scale regional bare-metal and cloud hypervisor fleets handling extreme diurnal burstiness across hundreds of thousands of concurrent background agent runs.
• Partner directly with RL and agentic model researchers so the same high-speed sandbox runtime powers both live user agents and million-rollout RL training loops.

TECHNICAL ENVIRONMENT & OFFERING
Stack: Rust, TypeScript, Go, Linux KVM / Firecracker / Cloud Hypervisor, overlayfs / FUSE / ZFS / NVMe-oF, eBPF/nftables, LSP / tree-sitter, Kubernetes & bare-metal Linux hosts. Workplace: Onsite in Palo Alto, CA. Compensation: $235,000 – $340,000 base salary plus high-upside hyper-growth equity, comprehensive healthcare, daily meals, and relocation support.

## Core Requirements

ESSENTIAL QUALIFICATIONS
• 6+ years of systems infrastructure engineering experience building cloud sandboxes, serverless container/VM runtimes, distributed filesystems, or developer cloud environments.
• Deep production mastery of Rust (or modern C++/Go) and Linux kernel primitives: KVM/Firecracker virtualization, namespaces/cgroups, memory snapshotting (`userfaultfd`), overlay/CoW filesystems, and virtual networking.
• Strong track record eliminating cold-start latency, tail-latency IO amplification, and noisy-neighbor contention on dense multi-tenant bare-metal hosts.
• Solid security engineering grounding in hypervisor isolation, egress filtering, and credential brokering.
• High-agency builder mentality excited to ship foundational infrastructure in small, autonomous engineering squads.

PREFERRED / BONUS EXPERIENCE
• Prior experience building cloud IDEs, CI/CD execution engines, serverless GPU/CPU microVM platforms, or RL coding-environment clusters.
• Familiarity with Language Server Protocol (LSP) internals, Nix/Bazel remote caching, or git virtual filesystems for massive monorepos.
• Open-source contributions to Firecracker, Cloud Hypervisor, containerd, Tokio, or developer tooling ecosystems.

## Application Schema & Direct Apply (`apply_for_role`)

Candidates and authorized AI agents on behalf of a candidate can submit an application via the declarative WebMCP form tool `apply_for_role` on https://jobs.talent247.co/jobs/staff-agentic-runtime-sandbox-engineer or via HTTP `POST https://jobs.talent247.co/api/public/jobs/staff-agentic-runtime-sandbox-engineer/apply` (`application/json` or `multipart/form-data`). Non-browser HTTP agents must include header `X-Talent247-Intake-Token` obtained from `GET https://jobs.talent247.co/api/public/intake-token` (or automatically returned in `GET https://jobs.talent247.co/api/public/jobs/staff-agentic-runtime-sandbox-engineer/form-schema`).

### Form Fields

- `full_name` (text, required): Full name
- `email` (email, required): Email
- `phone` (phone, optional): Phone
- `location` (text, optional): Location
- `linkedin_url` (url, optional): LinkedIn URL
- `cover_letter` (textarea, optional): Cover letter
- `consent` (checkbox, required): I consent to my data being processed for this application
- `cv_file` / `cv_base64` + `cv_filename`: Upload a CV in .pdf or .docx format (<= 10 MB) or provide an `https://` LinkedIn profile URL in `linkedin_url`.

### Alternative: Talent Pool Intake (`join_talent_pool`)

If this mandate is not an exact match, register once in the Talent247 Talent Pool at https://jobs.talent247.co/talent-pool (`https://jobs.talent247.co/talent-pool.md`) via WebMCP tool `join_talent_pool` or `POST https://jobs.talent247.co/api/public/talent-pool`.
