AI Engineer

Key Responsibilities:

• Build the agent execution runtime: Design and ship the layer that compiles a brief into a running team of agents — topology and handoffs, deterministic gates, the shared message bus, session lifecycle, and recovery behavior.
• Design the tool surface agents work through: Replace "here is a shell, please be careful" with typed, versioned toolpacks backed by reviewed repository recipes — sandboxed execution boundaries, lease handling, process-tree ownership, and MCP servers.
• Make quality measurable, then improve it: Build the evals, benchmarks, and metric sets that score a run; instrument the system with per-phase timing, structured error taxonomies, and cost attribution.
• Own the model substrate as a swappable input: Bind briefs to capability classes instead of vendor model names, work with routing and inference infrastructure across hosted and on-prem serving, and tune context, caching, and model selection.

What You'll Need:

• 5+ years of professional software engineering experience, including meaningful time building and operating LLM-backed systems in production.
• Hands-on depth with agentic systems: tool and function calling, multi-agent orchestration, context and prompt engineering, structured output.
• Strong developer-tooling instincts from building CLIs, build systems, CI/CD, internal platforms.

Nice to Haves:

• Experience with MCP — building servers or clients and designing tool interfaces that constrain what a model can do.
• Sandboxing and host isolation experience: process supervision, network and filesystem boundaries, resource leases.
• Release engineering background — bundling, artifact provenance, benchmarking against a baseline, staged promotion, and rollback.

Benefits:

• Competitive salaries and meaningful equity.
• Health, dental, vision, life, and disability insurance, plus 401(k) and flexible spending accounts (US).
• Flexible time off and remote work with an Atlanta office available.