AI Integration Engineer

Avanquest; Poland; On-site; PLN 180,000 - 270,000; Full time

Benefits offered by this job

Hybrid work model

Competitive pay

Insurance package

Bonus program

Generous vacation and time-off

Professional development

Diverse, multicultural environment

Office in Krakow

Job summary

Avanquest in Poland is seeking an AI Integration Engineer to own the model-serving API, AI-powered features, and the orchestration backbone of our document processing platform. This is a high-ownership, full-stack role for engineers who want to build real AI systems — not just wire up third-party APIs.

While we are open to remote work from anywhere in Poland, we also have a fantastic office in Krakow — a great place to collaborate in person, grab a coffee, and get to know the team if you'd

Qualifications

• 3+ years of experience across backend, API design, and web technologies.
• Proven track record deploying or integrating LLMs in production (open-source models strongly preferred).
• Hands-on knowledge of REST API design and at least one API framework.
• Experience building AI features in web apps, including streaming and async response handling.
• Familiarity with document processing workflows — OCR, parsing, classification at scale.
• Comfortable designing multi-step orchestration pipelines with task queues, retries, and failure handling.
• Strong communication skills; able to reason about trade-offs across latency, cost, and accuracy with stakeholders.

Responsibilities

• Evaluate and deploy open-source LLMs via vLLM, Ollama, or TGI on GPU infrastructure.
• Design and maintain a REST API with auth, rate limiting, versioning, and API documentation.
• Optimize inference: quantization, batching, and concurrency tuning for latency/cost trade-offs.
• Integrate AI features into our web apps and document processing platforms.
• Build AI-powered UI components: chat interfaces, inline suggestions, smart search, and summarization widgets.
• Collaborate with frontend engineers on UX patterns specific to async and streaming AI responses.
• Design multi-step orchestration pipelines for document ingestion, parsing, classification, and extraction.
• Integrate OCR, layout detection, and chunking strategies for PDFs, Word docs, spreadsheets, and scanned images.
• Build RAG pipelines with hybrid retrieval (dense + sparse) over document corpora.
• Implement task queues and async workers to handle high-volume document processing reliably.
• Write technical docs, so the platform is maintainable by the whole team and accessible for technology partners.
• Stay current on the open-source model ecosystem and advise on model selection and upgrades.

Skills

Backend development

API design

Web technologies

LLM deployment

Open-source models

REST API

Streaming / async

Tools

vLLM

Ollama

TGI

GPU infrastructure

Job description

At Avanquest, we build software that makes digital life genuinely easier, for everyday users and professionals alike, all over the world. Smooth document management, faster and safer devices, and browsing without the hassle: we spot the everyday frustrations and fix them. Millions of people around the world count on us. And we're just getting started.

We're growing fast, and we're hungry for more. With teams across North America and Europe, we tap into a wide range of perspectives to push our thinking further. AI isn't a buzzword here, it's a real engine for change. We use it to sharpen our products, break new ground, and build experiences that actually move the needle.

Creativity and boldness are welcome at every level. We don't want order-takers, we want builders. The best idea wins, no matter who it comes from. Here, personal ambition and team spirit don't compete, they feed each other. If you want to stretch yourself, make a real impact, and win as a team, you're in the right place.

We’re looking for an AI Integration Engineer to own the model-serving API, AI-powered web app features, and the orchestration backbone of our document processing platform. This is a high-ownership, full-stack role for engineers who want to build real AI systems — not just wire up third-party APIs.

While we are open to remote work from anywhere in Poland, we also have a fantastic office in Krakow — a great place to collaborate in person, grab a coffee, and get to know the team if you'd rather work on-site or just drop by from time to time.

What you'll be responsible for

Model Serving & API

• Evaluate and deploy open-source LLMs via vLLM, Ollama, or TGI on GPU infrastructure;
• Design and maintain a REST API with auth, rate limiting, versioning, and API documentation;
• Optimize inference: quantization, batching, and concurrency tuning for latency/cost trade-offs.
• Integrate AI features into our web apps and document processing platforms;
• Build AI-powered UI components: chat interfaces, inline suggestions, smart search, and summarization widgets;
• Collaborate with frontend engineers on UX patterns specific to async and streaming AI responses.

Document Orchestration

• Design multi-step orchestration pipelines for document ingestion, parsing, classification, and extraction;
• Integrate OCR, layout detection, and chunking strategies for PDFs, Word docs, spreadsheets, and scanned images;
• Build RAG pipelines with hybrid retrieval (dense + sparse) over document corpora;
• Implement task queues and async workers to handle high-volume document processing reliably.
• Write technical docs, so the platform is maintainable by the whole team and accessible for technology partners;
• Stay current on the open-source model ecosystem and advise on model selection and upgrades.

The profile we're looking for

• 3+ years of experience across backend, API design, and web technologies;
• Proven track record deploying or integrating LLMs in production (open-source models strongly preferred);
• Hands‑on knowledge of REST API design and at least one API framework;
• Experience building AI features in web apps, including streaming and async response handling;
• Familiarity with document processing workflows — OCR, parsing, classification at scale;
• Comfortable designing multi-step orchestration pipelines with task queues, retries, and failure handling;
• Strong communication skills; able to reason about trade‑offs across latency, cost, and accuracy with stakeholders.

Here’s what we offer

Working at Avanquest means thriving in an environment where performance and well-being go hand in hand. We believe in flexibility, balance, and ongoing professional growth.

Here’s what's waiting for you

• A flexible hybrid work model, with occasional opportunities to work remotely from abroad.
• Competitive pay that recognizes your value and your talent.
• An insurance package for you and your family.
• A bonus program that rewards your performance and your drive.
• A generous vacation and time‑off policy, because we believe in real rest.
• We’re committed to growing your potential and investing in your professional development.
• A stimulating, diverse, and multicultural environment where every perspective counts.

We value and support diversity. We are committed to providing an environment that promotes inclusion and respect for all. We therefore encourage women, people of all gender identities, Aboriginal people, and people with disabilities to apply for our positions.