Senior AI Software Engineer
Bucharest, Romania
The Senior AI Software Engineer will work in our Product Engineering team developing SEAL DocsIQ, the intelligent document processing module of our proprietary, globally successful enterprise software platform – SEAL. This role demands a professional with a minimum of 3 years of hands-on experience in building AI/ML solutions, ideally focused on document understanding, intelligent classification, AI-based metadata extraction, and Generative AI. The ideal candidate has deep practical expertise in Python, modern LLMs and frameworks (LangChain, LlamaIndex, Hugging Face), document AI models, and production-grade ML pipelines.
SEAL DocsIQ is the AI-powered intelligent document processing module of SEAL, delivering capabilities such as automatic document classification, AI-driven metadata and data extraction, document summarization, semantic search, and Gen-AI powered document Q&A and analysis.
JOB DESCRIPTION
Role:
- AI/ML Model Development & Integration:
- Design, develop, and deploy AI/ML models for document classification, entity extraction, metadata extraction, and document understanding.
- Integrate and fine-tune large language models (LLMs) and foundation models (e.g., OpenAI GPT, Anthropic Claude, open-source models) for document-centric use cases.
- Build and maintain Retrieval-Augmented Generation (RAG) pipelines for intelligent document Q&A and semantic search.
- Implement prompt engineering strategies and evaluate model performance systematically.
- Document Understanding & Processing:
- Develop pipelines for intelligent document ingestion, OCR, layout analysis, and content extraction from diverse document types (PDF, scanned images, Office formats).
- Implement and optimize document classification models (supervised, zero-shot, few-shot) with high accuracy and scalability.
- Build AI-based metadata extraction workflows using NLP, named entity recognition, and custom extraction models.
- Generative AI & Advanced NLP:
- Design and implement Gen-AI features including document summarization, automated report generation, and conversational document analysis.
- Work with frameworks such as LangChain, LlamaIndex, Haystack, or similar for orchestrating LLM-based workflows.
- Evaluate, benchmark, and select appropriate AI models and embedding strategies for production use.
- Production Engineering & MLOps:
- Build production-grade ML pipelines with proper versioning, monitoring, and automated retraining.
- Implement model serving infrastructure (REST APIs, batch processing) with focus on performance and reliability.
- Work with vector databases (e.g., Pinecone, Weaviate, Milvus, pgvector) for semantic search and retrieval.
- Ensure solutions are scalable, maintainable, and well-documented.
- Collaboration & Continuous Improvement:
- Work closely with product managers, software engineers, and domain experts to translate business requirements into AI solutions.
- Stay current with the rapidly evolving AI/ML landscape, evaluate emerging models, tools, and techniques.
- Contribute to technical design reviews, code reviews, and knowledge sharing within the team.
- Continuously learn and apply new skills and technologies to improve development practices.
You are an ideal candidate if you have:
- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or equivalent
- 5+ years of experience in software engineering with Python, with at least 3 years focused on AI/ML applications
- Strong practical experience with large language models (LLMs) and modern AI frameworks (LangChain, LlamaIndex, Hugging Face Transformers)
- Hands-on experience with document AI: OCR, layout analysis, document classification, and entity/metadata extraction
- Experience building RAG pipelines and working with vector databases
- Proficiency with NLP techniques: text classification, NER, semantic similarity, embeddings, and transformer architectures
- Experience with ML pipeline tools and MLOps practices (MLflow, Weights & Biases, DVC, or similar)
- Experience with prompt engineering, model evaluation, and fine-tuning techniques
- Solid understanding of REST API development (FastAPI, Flask) and microservices architecture
- Familiarity with databases: relational (PostgreSQL, MySQL) and non-relational (MongoDB, Elasticsearch)
- Experience with cloud platforms (AWS, Azure, or GCP) and containerization (Docker, Kubernetes) is a plus
- Good communication skills, with the ability to convey complex technical concepts to non-technical stakeholders
AXIVANT IS THE RIGHT PLACE FOR YOU! DISCOVER WHY!
Work with the best technologies! Created by us.
We know how important it is to have access to the latest technologies. At our company, we offer you the opportunity to work with cutting-edge software platforms, created by our very own experts (own IP) and successful at global level. With our innovative platforms and top-notch team, you’ll have everything you need to unleash your full potential and achieve your career goals.
Be part of a global success! Together with global partners and amazing customers.
Join our team and become part of a global success story. With the support of our global partners, you’ll have the opportunity to build and deliver complex solutions for major customers in top industries worldwide. Your expertise and dedication will play a critical role in shaping the future of our company and making a difference at global scale.
Put your personal mark on results! No limits for your ideas.
We encourage bold ideas and personal expression and creativity. We encourage you to put your personal mark on everything you do and push the limits of what’s possible. With no boundaries on your ideas, you’ll have the freedom to innovate and explore new possibilities. And when you achieve results, we’ll be there to celebrate your success and support your ongoing growth and development.
WE ARE LOOKING FOR EXCEPTIONAL COLLEAGUES!
Take the next step in your career and contribute to our global success! Complete the form bellow to apply!
