AI Agent Engineer

We are looking for an AI Agent Engineer with Full-stack and DevOps experience, particularly in bot generation. Ideally, you have a solid understanding of Bot making and production. You will turn static brands into living AI mascots. You’ll own the tech that spins up, hosts, and iterates 4-grade agents every month—then keeps raising the bar on speed, cost, and quality.

Key Responsibilities:

• Ship Fast: End-to-end ownership—prototype, deploy, iterate in ≤48-hour cycles.
• Integrate Everything: OAuth/webhook flows for X, Discord, TikTok, YouTube, etc.
• Automate Learning: Lightweight RAG + prompt-tuning pipeline that ingests fresh brand content hourly.
• Guard the Brand: Build moderation, rate-limiting, secret management, and policy filters.
• Measure & Grow: Push engagement metrics to PostHog/Supabase; run A/B tests on prompts.

KPI's:

• 4 agents/month shipped after 30-day ramp
• < 7 days cycle time (brief → prod)
• ≥ 10 % engagement rate on first-month posts
• < $0.05 token cost per outbound post (optimised prompts/caching)

Requirements

• 3 + yrs shipping production Node or TypeScript (NestJS, Next.js), Python (FastAPI, LangChain), and cloud deploys (Fly.io, Vercel, AWS, or GCP).
• Hands-on with LLMs (OpenAI, Claude, Gemini) and tooling (LangChain, LlamaIndex, AutoGen)
• Hands-on with LLM agent frameworks (ElisaOS, Auto-GPT, CrewAI, or custom).
• Live code that hits X/Twitter or Threads Graph API.
• DevOps you actually touched: Docker, CI/CD (GitHub Actions), basic observability.
• Proven ability to launch a customer-facing product in < 2 weeks (link, repo, or case study required).
• Real-time API work (OAuth, webhooks, rate-limit handling).
• Security best-practices: least-privilege IAM, secret rotation, basic SOC-2 awareness
• Bias for lean shipping—comfortable owning full lifecycle from prompt → prod monitor.
• Portfolio / GitHub that shows you can move fast without breaking things.
• Currently living in Latin America.

Nice to Have:

• Contributions to ElisaOS or other agent frameworks.
• Growth-engineering chops (viral loops, referral hooks).
• Multimodal generation (image / audio).
• Front-end polish (Next.js + Tailwind) for internal dashboards.
• Vector-DB chops (Supabase, Pinecone).
• Prompt engineering or copy flair.
• 3-D/WebGL or creative-coding hobby (helps with our blob visuals).
• Startup or small-team “first engineer” track record.

Our Recruitment Process

• Video Interview
• 20-minute take-home skills test
• 30-minute Call with the Recruiter (project, benefits, etc.)
• Interviews directly with the client (depending on the project the # of interviews may vary, this may include an assessment)
• Final Offer

Benefits

• Work remotely Monday - Friday, 40 hours a week (no weekends)
• Vacation: 10 business days a year
• Holidays: 5 National Holidays a year
• Company Holidays: 5 Company Holidays a year (Christmas Eve, Christmas Day, New Year's Eve, New Year's Day, Zipdev Day)
• Parental Leave
• Health Care Reimbursement
• Active Lifestyle Reimbursement
• Quarterly Home Office Reimbursement
• Payroll Deduction Purchase Plans
• Longevity Bonus
• Continuous Learning Bonus
• Access to Training and Professional Development Platforms
• Did we mention it's REMOTE?!!

One of our core values at Zipdev is "Be authentic." that's why we encourage you to answer the application form in your own words; we are interested in getting to know you, not a digital assistant.

Wondering how our remote environment or our payment method work? We've put together some helpful answers in our FAQs at the bottom our our career site. Take a look and let us know if you have any other questions!