G

AI Engineer, Production Agents

Guild.ai
2 hours ago
Full-time
On-site
San Francisco, California, United States
AI Engineer, Production Agents Guild.ai is looking for a founding engineer focused on building production agents—someone who will push our platform to its limits by creating some of the first real-world agents that developers rely on. Overview We’re tackling one of the hardest—and most important—problems in software engineering: helping developers understand, evolve, and operate complex systems using autonomous and event-driven AI. Your agents will be among the first proof points that this new way of building is not only possible, but better. What you will do

Build the first production agents: design, implement, and ship some of the earliest agents built on the Guild.ai platform—agents that developers will use to understand, debug, and evolve complex software systems. Push the platform by using it: act as both power user and core contributor, feed experience back into the platform’s APIs, abstractions, and UX. Own agent workflows end-to-end: take agents from idea → prototype → production—task scoping, architecture, prompts, tools, integrations, logging, and iteration based on real-world behavior. Integrate deeply with real developer environments: connect agents to source control, CI/CD, observability, and other components of modern engineering stacks so they can operate on real code and real systems. Make agents reliable, safe, and observable: implement guardrails, monitoring, and debugging tooling. Collaborate closely with product and evaluation teams: define agent behaviors, success metrics, and iteration loops. Use evaluation harnesses and telemetry to guide improvements. Shape the agent engineering practice at Guild.ai: help define patterns, libraries, and best practices for building agents on the platform.

What you will bring

Strong software engineering background and experience owning complex features or systems end-to-end. Hands‑on experience building with LLMs (prompting, tool calling, function calling, RAG, workflows) in a production or high‑stakes environment. Proficiency in Python and comfort with TypeScript or modern web/backend stacks; ability to design and reason about distributed or event‑driven systems, APIs, and integrations. A practical mindset around reliability: logging, observability, debugging, and iterative hardening of systems in production. Comfort operating in a high‑ambiguity, high‑ownership startup environment. Clear communication and a strong product sense—you care that what you build solves real problems for engineers.

Bonus points

Experience building agentic systems (tool‑using agents, workflow engines, multi‑step or multi‑agent setups). Familiarity with developer tools, infrastructure, observability, or platform products. Experience integrating with Git‑based workflows, CI/CD, cloud services, or internal tooling used by engineering teams. Prior work with evaluation or monitoring of LLM‑based systems in production. Experience at an early‑stage startup or in a role where you were the primary builder for a new product area.

Benefits & perks

Significant equity in an early‑stage, venture‑backed startup. Comprehensive health benefits (medical, dental, vision). Flexible PTO to ensure you have time to recharge.

Seniority level

Mid‑Senior level

Employment type

Full‑time

Job function

Engineering and Information Technology

Location San Francisco, CA #J-18808-Ljbffr