AI & Backend Engineer — Agentic Systems
Location: Remote
Type: Contract / Full-time
Experience: 4+ years software engineering experience
About the Role
We're a remote-first, US-based technology company looking for a hands-on AI & Backend Engineer to build AI-powered product capabilities and the backend systems that support them. You'll work directly with the founding technical team, with real ownership over where agents replace manual work entirely and where they augment it. If you want to build agentic systems that ship into production and get used immediately — not a lab project, not a demo — this is that role.
We are.
This is not a traditional backend role with AI added on. You’ll build AI agents and agentic workflows, integrate LLMs with application data and external services, and develop production systems using Python, TypeScript, PostgreSQL, and GCP/AWS.
We’re looking for someone who can move quickly from product requirements to working, production-ready solutions.
Responsibilities
- Build AI agents and multi-step agentic workflows using LLMs, tool/function calling, structured outputs, retrieval, and context management.
- Develop backend services and APIs using Python and TypeScript.
- Design and maintain PostgreSQL based schemas, queries, authentication, RLS, and data access.
- Integrate AI agents with internal data, APIs, and third-party services.
- Build reliable AI workflows with validation, retries, guardrails, observability, and appropriate human-in-the-loop controls.
- Deploy and operate services on GCP/AWS.
- Debug and optimize systems for reliability, performance, latency, and cost.
- Collaborate closely with product and engineering to turn ideas into working solutions.
Requirements
- Strong professional experience with Python and working knowledge of TypeScript/Node.js.
- Hands-on experience building production applications with LLMs and generative AI APIs.
- Experience building agentic systems, not just basic chatbot or prompt/response applications.
- Experience with frameworks/SDKs such as LangGraph, Google ADK, OpenAI Agents SDK, AWS Strands, or similar.
- Strong experience with PostgreSQL.
- Experience designing REST APIs and integrating third-party services.
- Understanding of authentication, authorization, OAuth2, JWT, RBAC, and API security.
- Experience deploying cloud applications, preferably on GCP.
- Strong problem-solving skills and ability to work independently.
Bonus Points
- GCP services such as Cloud Run, Pub/Sub, Cloud Functions, and Secret Manager
- RAG, embeddings, pgvector, and semantic search
- MCP and agent tool integrations
- Docker and CI/CD
- Event-driven architectures and background jobs
- AI evaluation, observability, and cost optimization
What We're Looking For
We want an engineer who understands that building production AI is more than calling an LLM API. You should be comfortable deciding when to use an agent vs. deterministic workflow, how agents safely access tools and data, and how to evaluate and improve AI reliability in production.
Education: Bachelor's degree in Computer Science or related field, or equivalent practical experience.
Sueldo: $1.311,05 - $3.374,67 al mes
Pregunta(s) de postulación:
- Have you shipped a production LLM agent system (not a demo)? Briefly describe it and the framework used.
- Which have you used in production: LangGraph, Google ADK, OpenAI Agents SDK, AWS Strands, or a custom framework?
- What is your desired compensation, in USD per month?
Lugar de trabajo: Empleo remoto
