Full Stack Engineer - AI

Responsibilities:

• Build real things. You'll write production code across the full stack: React frontends, Python/Node backends, ClickHouse queries, Kafka event pipelines, LangGraph agent workflows, and YAML-driven process definitions. Not prototypes. Not demos. Stuff that runs in production for real companies moving real cargo across real oceans.
• Talk to enterprise clients. You'll sit across from logistics managers, freight forwarders, and operations leads. You'll listen to their messy, exception-filled processes with 6 approval levels, 4 document types, and 3 systems that don't talk to each other and turn that chaos into structured workflows they can actually use. This isn't optional. It's the job.
• Think AI-first. Every problem you encounter, your first question should be: Can an agent handle this? Don't let me build a CRUD app. You'll design agents that extract fields from Bills of Lading, validate invoices against purchase orders, auto-route approvals based on business rules, and flag exceptions before humans even notice them. You'll work with LLMs, RAG pipelines, document parsers, and agent orchestration frameworks daily.
• Own problems end-to-end. You won't hand off a spec and wait. You'll identify the problem, design the solution, build it, configure it for the client, deploy it, watch it in production, and fix what breaks. The FDE model means you own outcomes, not tasks.

Requirements:

• You can code. Full-stack, independently, at production quality. You've built thingsnot just assignments, but projects, tools, and systems that other people actually used. You're comfortable across the stack, and you don't need hand-holding to ship a feature.
• You can communicate. You can explain a technical architecture to a non-technical client. You can run a discovery call. You can write a clear document. You can present without slides being your crutch. This is not a nice-to-have. Half the job is translating between the worlds of technology and business.
• You can think. When someone describes a messy process, you don't just nod; you ask why before how. You spot patterns underneath apparent chaos. You push back on unnecessary complexity. You can hold a system in your head and reason about what happens when things go wrong.
• You learn fast. You don't need to know logistics. You need to be the kind of person who, after two client calls and a week of reading, can hold their own in a conversation about bills of lading, demurrage charges, and Incoterms implications. Domain knowledge is teachable. Curiosity and raw learning speed are not.

The tech you'll work with:

• Frontend: React, React Flow (node-based graph editors).
• Backend: Python, Node.js, FastAPI.
• Data: ClickHouse, Kafka (event streaming), Debezium (CDC).
• AI/ML: LangGraph (agent orchestration), LLMs (prompt engineering, RAG, tool use), DPT-2 (document extraction), PageIndex (long-document reasoning), and Weaviate (vector search).
• Permissions: OpenFGA (Zanzibar-based relationship access control).
• Observability: Langfuse (LLM tracing), OpenTelemetry.
• Cost control: LiteLLM (gateway + budgets), Orkestra (model routing).
• Infrastructure: dbt (semantic layer / MetricFlow), Temporal (scheduling), DataHub / OpenMetadata (catalog).

Strong signals:

• You've built something with LLMs, not just used ChatGPT, but actually integrated an LLM into a working system. Prompt engineering, tool use, agents, RAG, or any of it.
• You've worked on a side project or open-source contribution that required you to understand a domain outside of CS.
• You can take a vague, messy brief and turn it into a structured plan without needing everything spelled out.
• You default to shipping over perfecting. You'd rather build a rough working version in 2 hours than spend 2 days on a flawless spec.
• You've done consulting, client-facing work, or been in a situation where you had to understand someone else's world to solve their problem.