> Markdown version of [/jobs/ext/4285790-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4285790-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# AI Engineer

- **Company:** Machinify, Inc.
- **Location:** United States
- **Experience:** Experienced
- **Salary:** $130,000.0 - $200,000.0
- **Contract:** Permanent contract
- **Skills:** LangGraph Framework, Artificial Intelligence, Information Extraction, JSON, Python (Programming Language), Language Modeling, Open Source Technology, OpenAI, Large Language Models, Claude Code, Caching, Agentic-AI, Git, Claude, Google Gemini
- **Published:** October 11, 2026
- **Apply:** https://www.juju.com/job/1_2E25539784584EE7A26899BD8754A7BD

## About the Role

What We're Looking For Required - 2-4 years of applied ML / AI engineering experience with a Bachelor's in CS, Math, Engineering or equivalent - or a Master's in a similar program with no prior industry experience required.
Either way, at least one production-quality system (industry, research, or substantial open-source) you owned end-to-end. - Strong Python engineering.
Clean abstractions, type discipline, async, tested code. - Deep, hands-on understanding of agent loops - how a m odel decides to call a tool, how a tool result re-enters context, how loops terminate, where they fail. - Hands-on experience with at least one major agent SDK - OpenAI Agents SDK, Anthropic SDK / claude-agent-sdk, LangGraph, or equivalent - and an opinion on the tradeoffs. - Working knowledge of how modern coding agents are built and how they engineer context - what goes in the system prompt, how files are read and edited, how long-running tasks are planned and tracked, where they break. - Fluency with Claude Code / Codex as a power user.
You should be able to brainstorm, plan, and execute non-trivial engineering tasks with these tools - including reading their source when needed to understand or extend behavior. - Solid command of VS Code and git - branches, rebases, worktrees, conflict resolution, PR workflows.
Not optional. - A bias toward measurement: you don't ship without an eval, and you don't believe a number you can't reproduce.
Strongly preferred - Experience designing structured outputs (Pydantic / JSON Schema) and tool interfaces that LLMs reliably call correctly. - Familiarity with reasoning models (o-series, Claude extended thinking, Gemini thinking) and a sense of when they earn their cost. - Prior work on long-context, citation-grounded systems where the m odel must point to evidence, not just answer. - Healthcare, legal, finance, or any other domain where "mostly right" is unacceptable.
Nice to have - Document understanding (OCR, layout-aware models, table extraction). - Vision-language models, multimodal retrieval. - Production experience with caching, observability, and cost control on LLM workloads.