AI Integration Engineer

Job Description

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. 

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.