AI Engineer (NLP, RAG)

Qualifications and requirements

- Hands-on AI/ML engineering for 5+ years, with strong production Python and a focus on building robust, scalable systems.

- Proven experience with advanced agentic RAG – hierarchical and/or multi-agent architectures.

- Hands-on RAG evaluation experience: defining and monitoring metrics to improve retrieval and response quality.

- Experience with advanced retrieval and pre-processing/chunking strategies (semantic chunking, late/latent chunking, re-ranking).

- Experience with GenAI orchestration frameworks (LangChain, LangGraph, or custom LLM orchestration layers).

- Hands-on with document intelligence / OCR services: AWS Textract and/or Azure Document Intelligence, plus Unstructured.io for parsing complex formats.

- MCP hands-on experience (or strong working knowledge and the ability to implement it).

- Data integration experience (with or without MCP); secure, efficient integration of third-party ML/AI services.

- Experience with cloud-native development on AWS: Docker, AWS ECS, Lambda.

- Solid understanding of event-driven architecture.

- Proficiency in Python and Pydantic, with strong knowledge of data pipelines and modular service design.

- Experience scaling RAG ecosystems across diverse data sources.

- Level of English – from Upper-Intermediate and above.

Projects

Andersen, an international IT outsourcing and custom software development company, is hiring an AI Engineer (NLP, RAG) for a project developing GenAI solutions, intelligent automation, and AI-powered knowledge management systems.

The customer is a global technology organization delivering digital products and business solutions to customers across multiple industries and markets. The company focuses on helping organizations improve operational effectiveness, optimize processes, and support business growth through the use of modern technologies, data-driven approaches, and scalable platforms.

The project is focused on developing AI-powered solutions that support digital transformation through intelligent document processing, knowledge retrieval, and automation. It includes building and enhancing production-grade GenAI applications that improve operational efficiency, decision-making, and access to critical information.

The role is aligned with Pacific Time Zone working hours.

Job functions

- Building hierarchical and multi-agent RAG systems with robust orchestration layers (LangChain, LangGraph; LlamaIndex is a plus).

- Ensuring the scalability and reliability of RAG ecosystems across diverse data sources.

- Applying advanced retrieval techniques – semantic chunking, late/latent chunking, re-ranking models.

- Defining and monitoring evaluation metrics to continuously improve retrieval quality and response accuracy.

- Implementing ingestion and parsing workflows using Unstructured.io, Pydantic, and custom ETL pipelines.

- Building and deploying services with Docker, AWS ECS, and Lambda, following event-driven architecture principles.

- Integrating third-party AI/ML services securely and efficiently.

- Participating in daily stand-ups, biweekly syncs, and technical interviews.

- Collaborating with distributed teams across multiple time zones.

- Contributing to strategic discussions on expanding the solution (agent development, model fine-tuning, new LLM use cases).

Conditions

- Experience collaborating with leaders in FinTech, Healthcare, Retail, and Telecom, including companies like Samsung, Siemens, and Johnson & Johnson.
- Opportunities to switch projects and develop expertise in various business domains.
- Flexible work conditions: fully remote, office-based, or hybrid options available.
- Professional, financial, and career growth guaranteed, with mentoring and adaptation systems for new employees.
- Potential to earn an additional $1,000 per month through company activities, included in the annual bonus.
- Access to a constantly updated corporate training portal with a comprehensive knowledge base.
- Engaging corporate culture with events like parties, game days, and snacks.
- Compensation for certifications (AWS, PMP, etc.).
- Referral program.
- Private health insurance and sports activity compensation.Join us!

Your personal data is protected in accordance with GDPR regulations. Learn more: https://andersenlab.com/privacy-policy

Desirable skills

- Experience with LlamaIndex and other GenAI orchestration tooling.

- Experience with Vision-Language Models (VLMs) for scanned-document/image understanding, and experience handling multilingual / encoding challenges in OCR.

- Model fine-tuning and domain-adaptation experience.

- Familiarity with AWS Bedrock (Claude/Sonnet) and Azure embeddings.

- Exposure to GCP Vertex AI.

- Advanced degree (MSc/PhD) in a relevant field, or research/publications in AI (CV/NLP).