Senior Software Engineer

Senior Software Engineer — Agentic Workflow & Craftsmanship Department: EngineeringClassification: Full-time, ExemptReports to: CTOLocation: US-only. No visa sponsorship. [Remote] About the role:Monarch Technology is a startup building enterprise agentic software. We're senior engineers who use AI to magnify our skills, which is a different sport than vibe-coding. In enterprise software, cost of change dominates everything else. If we were shipping mobile games or marketing sites, we'd have a different opinion. Modern best practices are changing every few months. The durable skills are related to craftsmanship and tinkering: taste, willingness to delete work, comfort with empirical iteration, the instinct to try the weird thing on a Saturday, and the discipline to measure rather than assume. You'll write code with agents, write code that orchestrates agents, build the surrounding quality machinery, and help the team converge on practices that hold up under real load. We live in the agentic world. It's different over here. We want someone who: • (A) Is all in on the XP / Craftsmanship model, including the human interactions. • (B) Likes startup speeds — build it today, release it tonight, refactor it tomorrow. Speed and maintainability. • (C) Has jumped into the AI space and tinkered their way to custom approaches for how they work in a modern workflow. • (D) Communicates well — in English and in code. Massive collaboration, mostly verbal. • (E) Has wrestled hard with modern agentic development in a way that's more interesting than prompt refinement. Specifically: • Deep commitment to craftsmanship: small units, clear naming, readable code, ease of change, ease of comprehension. • Strong opinions about testing, held loosely: comfortable with TDD, characterization tests, mutation testing, property-based testing — and knows when each is the right tool. • Practical, recent experience using coding agents for real work, with honest views about where they help and where they generate confident garbage. • Comfortable building tools and pipelines that tighten the agent loop and shorten feedback. • Understands that prompts shift distributions — they do not enforce bounds. Has an architectural answer for that. • Refactoring fluency: able to take a messy module to a clean one in small, safe steps. • Pragmatic methodology: familiar with XP, Lean, and related traditions. Uses what works, discards what doesn't. • Comfortable with statistical thinking about software behavior — confidence intervals, composition arithmetic, residual risk. • Clear written communication: can explain a tradeoff in a paragraph. #1 Requirement — recency over duration:You have hands-on agentic work from this year. In 2022, AI was different from ML because AI was written in PowerPoint. The best ways to use these tools, and the best tools themselves, have changed half a dozen times this year. Pre-2026 experience with agentic coding is background, not signal. Your enterprise software experience is not from this year. You've been in enough enterprises long enough to understand the differences. Cost of change, integration surface area, the half-life of a decision, what "done" means when something has to run for a decade. Prompt-engineering, intent-engineering, and algorithmic guardrails around LLM outputs are warmups. A motivated child could do those. We want to hear about what you've tried that's actually interesting. What we're not impressed by: • Spec-centric solutions — "I can simply prompt the agent better and it'll do what I want." Specs are a useful component inside a stacked architecture. They are not the architecture. If your answer is "make the spec better," we're done. • Massive hardcoded limiters — agent does X, but 3,000 lines of algorithmic control on 20 lines of spec. Not a real solution either. If your answer is "put guardrails on the spec," we're done. • Resume-decorated alphabet soup. "I've done RAG, evals, tool use, MCP, observability." Cool — most people have, and most of it sucks. Tell us about specific things you've built and what changed when you ran them in anger. • Performative obsession with token cost. We'll monitor it eventually. It's not a focus today. If you lead with "I cut prompt tokens by 40%," we'll roll our eyes. • People who have only ever done spec-centric work, or who have rejected specs entirely. The candidate we do want: someone who tried spec-centric, hit the wall, and now uses specs as components inside a stacked architecture. Minimum requirements: • Education: Bachelor's in Computer Science, related field, or equivalent demonstrable experience. • Experience: Production software experience with strong craftsmanship discipline. Recent (THIS-year) hands-on engagement with current-generation coding agents (Claude Code, Codex, or comparable), and evidence of having changed your mind at least once about how to use them. Duration is not the metric. Recency and disposition are. • Systems: Strong in at least one mainst