Descrição da Vaga
We're looking for a Full Stack Engineer to own and ship product end to end at a fast-moving global talent company. You will build across the full stack using TypeScript, Node.js, React, Next.js, Tailwind, and Postgres, with a heavy focus on LLM integration and AI agent engineering. This is an internal role.
One thing matters more than anything else here: your ability to independently own a project, execute it without hand-holding, ship something that works, and produce real results. We are not looking for someone who waits for detailed specs or needs constant direction. We are looking for someone who takes a problem, figures out the best solution, builds it, ships it, and iterates. If you are a strong full stack engineer with genuine AI and agent engineering experience who can work autonomously and deliver, this role is a strong fit.
Why You'll Want to Join
You will be paid in USD (bi-monthly: every 15th and 30th)
Paid Time Off in accordance with company policy
Observance of Holidays per company guidelines
100% remote setup so you can work wherever you're most productive
This role requires availability during US Eastern Time business hours
Work directly with founders on internal tools and AI-powered systems that shape how the company operates
High-ownership engineering role with full autonomy over how you build and ship
What You'll Work On
LLM and AI Agent Engineering
Design, build, and deploy LLM-powered workflows and AI agents that solve real operational problems
Integrate large language models into internal products and automate complex, multi-step processes
Build agent logic, tool use, memory systems, and orchestration layers that work reliably in production
Continuously improve AI system reliability, accuracy, and performance based on real usage
Full Stack Product Development
Build and ship full stack features and internal tools across the entire stack independently
Develop frontend interfaces using React, Next.js, and Tailwind that are clean, fast, and functional
Build backend services, APIs, and data layers using Node.js and Postgres
Own the full lifecycle of every project from scoping through deployment and iteration
Ownership and Execution
Take ambiguous problems and turn them into working software without requiring detailed specs
Make sound architectural decisions independently and execute on them with precision
Ship fast, iterate based on real feedback, and maintain a high bar for output quality
Proactively identify opportunities to improve systems, reduce friction, and build things that make the team faster
What You Bring
Strong, production-proven full stack engineering experience across TypeScript, Node.js, React, Next.js, Tailwind, and Postgres
Genuine, hands-on LLM and AI agent engineering experience — this is the most important technical requirement
Demonstrated ability to independently own projects end to end and ship working software without constant direction
Comfortable making architectural decisions and building from scratch in ambiguous environments
Strong engineering judgment with the ability to scope, prioritize, and execute without a formal playbook
Excellent written communication for async collaboration in a remote environment
Available to work during US Eastern Time business hours
Nice to Have
Experience with AI orchestration frameworks such as LangChain, LlamaIndex, Vercel AI SDK, or similar
Background building internal tooling or automation systems for operational teams
Experience working in a lean startup or early-stage company where you were the primary or sole engineer
Familiarity with deployment and infrastructure tooling such as Vercel, Railway, or similar
Prior experience building RAG pipelines, multi-agent systems, or tool-use integrations
How to Apply
Please include:
Your updated resume
A portfolio link or GitHub showing projects you have built and shipped, with a focus on any LLM, agent, or AI-powered work
A short Loom video (1 to 2 minutes) introducing yourself, walking through a project you are most proud of, and explaining the technical decisions you made and how you drove it from idea to shipped product independently
Only candidates who submit both a portfolio and Loom video will be moved to the next step of the hiring process.
If you are a strong full stack engineer who can build real AI-powered systems, work independently without being managed, and ship things that actually work and produce results, this role gives you the autonomy and the direct impact to do your best work.
Application Process Overview
Our comprehensive selection process ensures we find the right fit for both you and our clients:
Initial Application - Submit your application and complete our prequalifying questions
Video Introduction - Record an video introduction to showcase your communication skills and work experience
Role-Specific Assessment - Complete a homework assignment tailored to the position (if applicable)
Recruitment Interview - Initial screening with our talent team
Executive Interview - Meet with senior leadership to discuss role alignment
Client Interview - Final interview with the client team you'd be supporting
Background & Reference Check - Professional reference verification
Job Offer - Successful candidates receive a formal offer to join the team
Each stage is designed to evaluate your fit for the role while giving you insights into our company culture and expectations. We'll keep you informed throughout the process and provide feedback at each step.
Ads