AI Engineer
About TheTop
We’re a small, fast-moving team with a US-based business side. No layers of management. No endless approval chains. Ideas go from experiment to production in days, not quarters.
Intro
TheTop is an early-stage AI startup. We’re looking for a Strong Middle Python & AI Engineer to help us scale TheEngine, working directly with our engineering lead and CTO.
This is a 0-to-1 role. You won’t just implement tickets. You’ll help shape the architecture, run experiments to find the right approach, and make the engine faster, smarter and cheaper to run. We’re looking for someone who is genuinely entrepreneurial about AI and comfortable working where the path isn’t fully defined yet.
What You’ll Do
- Build and improve the core engine mechanisms: model routing, prompt and semantic caching, organizational memory, and cost accounting
- Run research and experiments, such as router quality, cache hit rates and memory benchmarks, and turn the findings into real technical decisions
- Extend provider coverage and the integrations customers connect through (API gateway, Claude Code, chat connectors)
- Build and scale backend services with Python + FastAPI on AWS
- Work shoulder-to-shoulder with the engineering lead and CTO, with direct exposure to enterprise customers
Requirements
- 3+ years of experience in backend or full-stack development
- Strong knowledge of Python, API design, and web frameworks
- Hands-on experience building AI products: real work with LLM APIs and the architecture around them (not just calling a model once)
- Comfortable reasoning about LLM cost/latency trade-offs, prompting, context windows, and token economics
- Experience with external integrations and background processing
- Entrepreneurial, research-driven mindset: you like proving ideas with experiments, not just opinions
- Self-driven and comfortable working in early-stage, ambiguous environments
Will Be a Plus
- Experience with LLM gateways/proxies (LiteLLM, Portkey or similar), model routing, or semantic caching
- Familiarity with vector DBs, RAG, memory systems (Mem0 or similar), and agent frameworks
- Experience with AWS (ECS, Terraform) and multi-tenant or isolated per-customer deployments
- Experience shipping developer-facing APIs or B2B SaaS for enterprise customers
- Familiarity with TypeScript/React
- Startup or solo project experience
What We Offer
- Full ownership of your technical direction
- Flexible working hours and remote-first setup
- Direct collaboration with the engineering lead, CTO and founders
- A product already running production traffic for enterprise customers, and a chance to shape it from 0 to 1
How to Apply
Send a short intro (which AI products you’ve built and why AI infrastructure interests you) and your CV with salary expectations.