AI Integration Engineer

Avanquest is the software publishing subsidiary of Claranova, a French group of innovative technological solutions, established in many countries, with revenues exceeding $500 million. At Avanquest, we create reliable and intuitive software solutions that satisfy our customers through 3 key product types: PDF software, photo editing software (Inpixio), and utility software to improve PC performance and security. Mainly offered as Software as a Service (SaaS), our products are sold in more than 150 countries and are translated into more than 15 languages worldwide.

Avanquest is:

• a multicultural collaborative group;
• an ambitious company in rapid development;
• a place where each Talent has its place to contribute its know-how and have a real impact on large-scale projects;
• an environment where productive initiatives are always recognized at their true value.

Visit our website : www.avanquestgroup.com

Job details :

We’re building AI deeply into our product stack — from open-source model serving to the interfaces our users interact with every day. As an AI Integration Engineer, you’ll own three interconnected layers: a model-serving REST API, AI-powered web app features, and the orchestration backbone of our document processing platform. This is a high-ownership, full-stack role for an engineer who wants to ship real AI systems, not just call third-party APIs.

(Only for candidates who are currently in Poland)

Model Serving & REST API

Deploy open-source LLMs and expose them through a versioned, production-grade API.

Web App Integration

Embed AI capabilities into our web interfaces — streaming UX, real-time features, and AI-powered components.

Document Processing Orchestration

Build the processing pipelines that extract, classify, transform, and act on documents at scale.

Key Responsibilities :

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;
• Own observability — latency, throughput, GPU utilization, and cost-per-call dashboards.

Web App Integration

• 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;
• Manage API keys, usage metering, and per-user AI feature flags on the client layer.

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;
• Design and optimize prompts for extraction, summarization, classification, and conversational AI workflows;
• Implement task queues and async workers to handle high-volume document processing reliably.

Platform & Collaboration

• Define evals and quality benchmarks for extraction accuracy, classification, and generation quality;
• Write technical docs, so the platform is maintainable by the whole team and accessible for technology partners;
• Partner with product, data science, and DevOps/MLOps to ship AI features reliably and at scale;
• Stay current on the open-source model ecosystem and advise on model selection and upgrades.

Requirements:

• 3+ years of software engineering experience spanning backend, API design, and web technologies;
• Proven experience deploying or integrating LLMs in production — open-source model experience strongly preferred;
• Hands-on knowledge of REST API design principles and at least one API framework;
• Experience building or integrating AI features in a web app, including streaming/async response handling;
• Familiarity with document processing workflows — parsing, OCR, extraction, or classification at scale;
• Comfort 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.

What we offer:

• A fair compensation for your value;
• Bonus program, paid vacation leave and competitive corporate benefits;
• We are committed to maximizing your potential and ensuring your professional development.
• Interaction with local and international teams;
• A friendly and collaborative work environment, where authenticity and well-being are a priority.