AI Backend Engineer, Agents & LLM Systems

We are looking for an engineer who can build production-grade AI systems: agents, LLM workflows, backend services, data pipelines, and AI product features.

You do not need to work in one specific language. You can use Python, TypeScript, Go, Java, Rust, or another strong backend language. What matters most is that you can build reliable AI systems, ship fast, and own work end to end.

This role requires valid US work authorization or a US visa, since the work involves US-based client collaboration, timezone overlap, and project delivery.

What You’ll Do

• Build AI agents, LLM workflows, RAG systems, tool-calling flows, prompt/context pipelines, and AI automation systems.
• Design and ship backend APIs, services, queues, data pipelines, and integrations that power AI product features.
• Work with LLM providers, embeddings, vector search, retrieval, evals, and model output quality checks.
• Build reliable AI systems with retries, guardrails, observability, cost control, latency optimization, and failure recovery.
• Turn messy real-world data such as documents, web data, customer data, logs, and third-party APIs into useful AI workflows.
• Own features from idea to production, working closely with founders, product, customers, and engineering.

Required

• Strong backend engineering ability.
• Hands-on experience building with LLMs, AI agents, RAG, prompt engineering, context engineering, evals, or AI workflow automation.
• Ability to design production systems: APIs, databases, background jobs, integrations, and deployment workflows.
• Strong ownership and product sense.
• Ability to work independently in a fast-moving startup environment.

Nice To Have

• Any one of these is enough: cloud infrastructure, Docker/Kubernetes, ML/NLP, data engineering, scraping, vector databases, eval frameworks, security, developer tools, or production observability.