Full Stack AI Engineer

**Zalion is an international AI start-up revolutionizing industrial procurement.** We use cutting-edge AI agents to automate manual Source-to-Pay processes, freeing up procurement teams for strategic work. We are live with the largest companies in Europe & the US. We love what we do. We get stuff done. We progress fast. **Zalion is an international AI start-up revolutionizing industrial procurement.** We use cutting-edge AI agents to automate manual Source-to-Pay processes, freeing up procurement teams for strategic work. We are live with the largest companies in Europe & the US. We love what we do. We get stuff done. We progress fast. ## Tasks * **Own and ship agent-powered features end-to-end** – from idea and prototype to production rollout and iteration. * Design, build, and deploy **AI agents in production** that interact with real systems (ERPs, email, supplier portals) and deliver measurable outcomes. * Work with both **structured and unstructured data** (RFQs, emails, quotes, contracts) to power memory, retrieval, and decision-making. * Build scalable **memory, reasoning, and orchestration pipelines** using tools like LangChain/LangGraph and evaluation frameworks. * Integrate with **external APIs and legacy systems**, dealing with real-world messiness, rate limits, and failure modes. * Contribute to our **cloud infrastructure** for scalable agentic workloads (observability, CI/CD, reliability, cost-awareness). * Solve hard problems around **context management, latency, robustness, and guardrails** – making agents debuggable and trustworthy, not magic. ## Requirements * Strong **Python** skills and a track record of writing clean, maintainable, well-tested backend code * Solid experience designing and building **RESTful APIs** and data models in production environments * Experience with **data engineering** concepts (ETL, data quality, performance) and backend architecture * Hands-on experience building something **real with LLMs** (OpenAI, Claude, etc.) – side projects are fine as long as they’re concrete * Comfort working in the **cloud** (ideally AWS) with CI/CD, logging, and monitoring * **A builder mindset** – you like to ship small, iterate quickly, and own your work end-to-end * Comfort with **ambiguity and ownership**: you spot problems, propose solutions, and drive them to completion without waiting for perfect specs * Roughly **4+ years** of professional experience, including at least one role where you owned a production service, subsystem, or major feature. ## Benefits * Build AI agents that actually _do_ things * Massive autonomy, zero bureaucracy * Immediate impact, your work ships fast to real customers * Modern stack, no legacy * Competitive salary + meaningful equity * High-end equipment 🛠️ **Tech Stack You’ll Work With** * **Python** (LangChain, LangGraph, LangSmith, FastAPI) * **AWS** (Bedrock, ECS Fargate, Lambda, S3, SQS/SNS) * **Next.js**, **React**, **TanStack Query/Router** * GitHub CI/CD , Sentry & Grafana & Prometheus * **Postgres**, **Redis** * Large Language Models (LLMs) and AI infrastructure (evaluation, tracing, guardrails) * Whatever the **future** brings that helps us ship faster and better

Tasks

* **Own and ship agent-powered features end-to-end** – from idea and prototype to production rollout and iteration. * Design, build, and deploy **AI agents in production** that interact with real systems (ERPs, email, supplier portals) and deliver measurable outcomes. * Work with both **structured and unstructured data** (RFQs, emails, quotes, contracts) to power memory, retrieval, and decision-making. * Build scalable **memory, reasoning, and orchestration pipelines** using tools like LangChain/LangGraph and evaluation frameworks. * Integrate with **external APIs and legacy systems**, dealing with real-world messiness, rate limits, and failure modes. * Contribute to our **cloud infrastructure** for scalable agentic workloads (observability, CI/CD, reliability, cost-awareness). * Solve hard problems around **context management, latency, robustness, and guardrails** – making agents debuggable and trustworthy, not magic.

Requirements

* Strong **Python** skills and a track record of writing clean, maintainable, well-tested backend code * Solid experience designing and building **RESTful APIs** and data models in production environments * Experience with **data engineering** concepts (ETL, data quality, performance) and backend architecture * Hands-on experience building something **real with LLMs** (OpenAI, Claude, etc.) – side projects are fine as long as they’re concrete * Comfort working in the **cloud** (ideally AWS) with CI/CD, logging, and monitoring * **A builder mindset** – you like to ship small, iterate quickly, and own your work end-to-end * Comfort with **ambiguity and ownership**: you spot problems, propose solutions, and drive them to completion without waiting for perfect specs * Roughly **4+ years** of professional experience, including at least one role where you owned a production service, subsystem, or major feature.

Benefits

* Build AI agents that actually _do_ things * Massive autonomy, zero bureaucracy * Immediate impact, your work ships fast to real customers * Modern stack, no legacy * Competitive salary + meaningful equity * High-end equipment 🛠️ **Tech Stack You’ll Work With** * **Python** (LangChain, LangGraph, LangSmith, FastAPI) * **AWS** (Bedrock, ECS Fargate, Lambda, S3, SQS/SNS) * **Next.js**, **React**, **TanStack Query/Router** * GitHub CI/CD , Sentry & Grafana & Prometheus * **Postgres**, **Redis** * Large Language Models (LLMs) and AI infrastructure (evaluation, tracing, guardrails) * Whatever the **future** brings that helps us ship faster and better