3+ years of professional software engineering experience, with strong proficiency in Go or Python
Experience taking an AI application from prototype to production use and supporting it afterward
Hands-on experience with agent patterns: tool and function calling, multi-step orchestration, and handling incorrect model output
Experience building and evaluating retrieval systems, including measuring quality against a baseline using held-out data
Experience designing controls for automation that acts on production systems, such as approval steps, idempotency, and audit trails
Experience diagnosing failures in LLM applications and fixing the underlying cause rather than the symptom
Experience with observability for LLM applications, including tracing, cost, and latency
Working knowledge of Kubernetes and experience deploying services through CI/CD
Experience integrating with third party APIs, including authentication and secrets handling
Experience building conversational or chat-based interfaces for internal users
A background in infrastructure, SRE, or technical support, and comfort reading logs and metrics from a live system
Experience testing both deterministic and non-deterministic systems
Experience with fine-tuning or building training datasets from production data
Open source contributions to AI tooling or agent frameworks
Wondering if you're a good fit? We believe in investing in our people, and value candidates who can bring their own diversified experiences to our teams – even if you aren't a 100% skill or experience match. Here are a few qualities we've found compatible with our team. If some of this describes you, we'd love to talk
You can tell the difference between the thing that's interesting and the thing that's urgent, and you'll say so out loud when they aren't the same
You've worked with a team that already had tooling they liked, and found the integration instead of arguing for a rewrite
You'd rather sit in on a real incident than infer how the work goes from a ticket
Blunt feedback from the engineers using your software is the most useful thing you'll hear all week, and you don't get defensive about it