AI Backend Engineer

Amego, Inc.; Deutschland; Vor Ort; EUR 90.000 - 150.000; Vollzeit

Zusammenfassung

Amego, a leader in mobile event technology, is seeking an AI Backend Engineer to build LLM-powered features for our product. You’ll join our engineering team, wire our Node.js/NestJS backend to large language models like Claude and OpenAI, and design production-grade services with robust AI tooling and monitoring.

This role emphasizes deep work with LLM APIs, prompt design, retrieval systems, and scalable architectures, while collaborating with a React frontend and ensuring reliable, cost-aware

Qualifikationen

• Strong backend engineering with Node.js/NestJS or equivalent.
• Hands-on experience with LLM APIs and SDKs (Anthropic, OpenAI, etc.).
• Experience implementing Retrieval-Augmented Generation (RAG) with embeddings and vector stores.
• Solid understanding of prompt engineering and token economics.
• Experience designing REST or GraphQL APIs for frontend teams.

Aufgaben

• Design, build, and maintain NestJS backend services powering LLM-driven features.
• Integrate with LLM providers via SDKs and APIs, including streaming responses and tool calling.
• Design and implement RAG pipelines, embeddings, vector search, and context assembly.
• Build and optimize prompt templates and orchestration logic.
• Own the data layer for AI features: vector stores, caching, and indexing.

Kenntnisse

Node.js

NestJS

LLM APIs

REST APIs

GraphQL

TypeScript

React

CI/CD

Tools

Pinecone

Weaviate

pgvector

Qdrant

Jobbeschreibung

Experience the future of events with Sidekick™. The AIupgrade your event app deserves.

We're looking for an AI Backend Engineer to join our engineering team and help build the LLM-powered features driving our product forw

Full time

About the job

Responsibilities

Requirements

About Us

Amego is the leading provider of mobile event technology solutions for event marketing teams. Our platform was forged through the demanding experience of some of the world’s largest events and is designed to make event planning easier, faster and more reliable than ever before. We provide mobile apps for live events for the B2B world's leading brands, quickly deploying branded, EMS-integrated native mobile apps that delight attendees and create an easy-to-manage SaaS solution for event organizers.

Come join us to have your code used by hundreds of thousands of attendees at events for brands you use every day. Amego powers some of the biggest events in the world in signature conferences by S&P500 software companies, pharmaceutical companies, financial services companies, and more. Our work is demanding but exciting - you build features that enable the best experiences for attendees at live events.

Job Overview

We're looking for an AI Backend Engineer to join our engineering team and help build the LLM-powered features driving our product forward. You'll work primarily in our Node.js/NestJS backend, designing and shipping the services that connect our growing React application to large language models like Claude and OpenAI. This role sits at the intersection of solid backend engineering and applied AI — you'll need to write production-grade, well-tested services, and also be comfortable working deeply with LLM APIs, prompt design, retrieval systems, and the operational quirks of running AI in production.

Key Responsibilities

• Design, build, and maintain backend services in NestJS that power LLM-driven features across our product.
• Integrate with LLM providers (Anthropic Claude, OpenAI, and others) via their SDKs and APIs, including streaming responses, function/tool calling, and structured outputs.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines — chunking strategies, embeddings, vector search, and context assembly.
• Build and optimize prompt templates and orchestration logic, with an eye toward reliability, cost, and latency.
• Own the data layer supporting AI features: vector stores, caching, and pipelines for ingesting and indexing content.Implement guardrails around AI features: rate limiting, retries, fallback models, output validation, and monitoring for hallucinations or failures.
• Collaborate closely with frontend engineers building the React client, defining clean APIs and contracts for AI-powered UI features.
• Instrument and monitor LLM usage (cost, latency, token consumption, error rates) and help the team make informed build-vs-buy and model-selection decisions.
• Write clear technical documentation and participate in code review, architecture discussions, and on-call rotations.

Qualifications

• Strong backend engineering experience, ideally with Node.js and NestJS (or a comparable framework like Express, Fastify, or a similar typed backend stack).
• Hands-on experience building production features with LLM APIs and SDKs (Anthropic, OpenAI, or similar) — not just prototypes or personal projects.
• Practical experience implementing RAG systems, including embeddings, vector databases (e.g., Pinecone, Weaviate, pgvector, Qdrant), and retrieval/ranking strategies.
• Solid understanding of prompt engineering techniques and the tradeoffs between different models, context window management, and token economics.
• Experience designing REST or GraphQL APIs that a frontend team can build against confidently.
• Comfort with asynchronous, event-driven, or queue-based architectures (e.g., BullMQ, Kafka) for handling long-running AI jobs.
• Familiarity with TypeScript across the stack; experience working alongside a React frontend is a plus.
• A pragmatic approach to testing, observability, and reliability — you think about what happens when a model call times out or returns garbage, not just the happy path.
• Strong communication skills and comfort working in a small, fast-moving team where ownership extends beyond your immediate ticket.

Nice-to-Haves

• Experience with agentic workflows, tool use, or multi-step LLM orchestration frameworks (e.g., LangChain, LlamaIndex, or custom orchestration).
• Experience fine-tuning or evaluating models, or building eval harnesses for LLM output quality.
• Background with streaming protocols (SSE, WebSockets) for real-time AI interactions in a UI.
• Experience with cost optimization strategies for LLM-heavy applications.

Why Join Us

You'll be one of the engineers shaping how AI actually gets built into our product — not bolted on as a demo, but engineered as a core, reliable part of the experience. You'll have real influence over architecture decisions, model choices, and the patterns the rest of the team follows as AI becomes a bigger part of what we ship.

You can work anywhere in the world. Amego offers competitive salary and benefits, and the opportunity for travel to some of the world's best cities to support our apps.