AI Engineer (Agentic Systems & LLM Workflows)

About the Role

We're not looking for someone who "has experience with AI" we're looking for someone who builds with it every day. An engineer whose default instinct is to reach for an LLM, an agent framework, or a durable workflow instead of writing another for-loop.

This is a high-ownership, high-output role. You'll design and ship agentic systems that touch real users and real money. You'll work alongside a product team that moves fast and expects the same. If your idea of a good week is shipping an internal tool on Monday, wiring up a RAG pipeline on Wednesday, and deploying a Discord bot by Friday, read on.

What You'll Build

• Multi-step AI agents that handle complex, real-world workflows end to end
• RAG pipelines that actually perform — not just LangChain defaults
• Durable background workflows for processing, enrichment, and orchestration
• Internal dashboards, admin tools, and integration surfaces (Slack, Discord, Intercom)
• Eval harnesses to measure and improve model performance over time
• The glue layer between LLMs, APIs, databases, and product features

What We're Looking For

Languages & Foundations

• Python 3.12 as your primary language — you live in the AI/ML ecosystem; FastAPI for AI/agent service APIs

• TypeScript (strict) in a monorepo on Bun + Turborepo — Next.js (App Router), React, Tailwind, shadcn/ui for UI; Hono + tRPC for the API layer; Better Auth for authentication

• Comfortable with SQL and Drizzle ORM with PostgreSQL — comfortable querying and working with a relational data model

LLM & Agent Tooling

• Hands-on with Anthropic, OpenAI, and Google Vertex AI (Gemini) APIs — function/tool calling, structured outputs, prompt caching; multi-provider failover via OpenRouter and Cloudflare AI Gateway
• Production experience with an agent framework: LangGraph for agent/AI services — not just a weekend project
• Familiar with Model Context Protocol (MCP) — building and consuming MCP clients/servers to extend agent capabilities
• You know the boring-but-critical stuff: streaming, retries, token cost management, rate limiting

RAG & Retrieval

• Experience with vector DBs: pgvector (preferred), Pinecone, Weaviate, or Qdrant
• Intentional about embedding models and chunking strategy — you've reasoned about trade-offs, not just accepted defaults
• Implemented hybrid search (BM25 + vector) when precision matters

Orchestration & Workflows

• Code-first workflow experience: BullMQ + Redis for queues, scheduled jobs, and durable background orchestration
• Aware of low-code tools: n8n, Zapier, Make — can use them when appropriate
• Background jobs, queues, and scheduled tasks are second nature

Evals & Observability

• Active user of at least one eval/observability platform: Langfuse (self-hosted) for tracing and evals — our primary observability platform; familiarity with LangSmith, Braintrust, or Helicone is a plus
• You've actually run an eval set — you have opinions on what makes a good one

AI-Native Dev Workflow

• Claude Code is your daily driver — plus comfort operating within a homegrown agentic-dev layer (hooks, skills, subagents)
• You ship internal tools in days, not sprints
• You have a "vibe coding" instinct — but you don't let it erode eng discipline

Infrastructure

• Comfortable deploying on AWS (EC2, S3, SES, ECR, Parameter Store) in us-east-2; Docker / Docker Compose for dev and prod; Caddy for TLS and reverse proxy; GitHub Actions + OIDC for CI/CD
• Docker / Docker Compose, env management, and secrets handling (AWS Parameter Store) are table stakes
• Some Biome, Vitest, and Playwright familiarity is a plus for linting, unit testing, and end-to-end testing

Product Glue

• Can spin up Next.js (App Router) / React dashboards and admin interfaces when needed
• Familiar with Discord.js, Slack API, and Intercom API ; comfortable with Asana, Fellow, and Google Workspace (Drive/Calendar/Gmail) integrations
• Understands product instrumentation with Mixpanel or GA4

Bonus Points

• You've built LLM-powered side projects that real people actually use
• You understand trading or trading platforms — this accelerates your empathy with our users enormously
• You have genuine opinions on model selection (Claude vs. GPT vs. open-weight) — you don't treat them as interchangeable black boxes

What You Won't Find Here

• Bureaucracy slowing down good ideas
• Sprints that stretch a one-day task into two weeks
• A team that's "exploring AI" — we're building with it

Success in This Role Looks Like

• 30 days: You've shipped at least one agentic workflow or internal tool to production. You understand the codebase, the data model, and where the biggest leverage points are.
• 60 days: You own a meaningful system — a RAG pipeline, a durable workflow, a Discord or Intercom integration — and it's running reliably with observability in place. You've run your first eval set on a prompt-sensitive workflow.
• 90 days: You're proactively identifying new places where AI can reduce manual work or improve trader experience. Your code is in production and measurably working. The team is shipping faster because of the systems you've built.
• Long-term: You're the person we call when a new LLM capability drops and we need to figure out what it means for our stack. You've built things traders and the internal team actually rely on daily.

Why Join Tradeify

• You'll work on a real, fast-moving product. We're not a research team or an internal tools shop. Our platform serves thousands of traders. The things you build get used immediately and the feedback loop is short.
• AI is a first-class priority, not an afterthought. We're investing heavily in agentic workflows, intelligent tooling, and AI-powered trader support. You'll have room to do genuinely interesting work, not just prompt-wrap CRUD apps.
• Small team, high ownership. You won't be one of twenty engineers on a feature squad. You'll have direct influence on architecture and product decisions from day one.
• The domain is genuinely interesting. Futures trading, risk management, payout systems, trader performance analytics — there's no shortage of complex, high-stakes problems worth solving well.
• We use the tools we ask you to know. Claude Code, LangGraph, Langfuse — these aren't on the JD to sound current. They're in our stack.