AI Engineer NLP (Python & Go – Bridging ML and Platform)
At a glance
Mid-level Machine Learning Engineering role at ARTIDIS. Zagreb · full-time.
Pay not stated Machine Learning Engineering salary
aimlroles summary, based on the employer's posting.
What you'll do
- Build and ship agentic NLP and LLM workflows across Python machine-learning pipelines and Go backend services
- Translate needs between ML and platform teams, shaping backend designs around model requirements
- Develop in both codebases and connect them through clear interfaces and reliable service integration
- Design LLM orchestration, APIs and service communication, then add evaluation and monitoring across models and services
- Keep AI systems reliable and performant for regulated medical use while delivering features from research into production
What you bring
- Strong Python skills, including object-oriented design, type-safe development and production-quality testing
- You have built and deployed NLP or LLM systems for production use
- You bring backend development experience or strong proficiency in Go, including API and service design
- You understand current NLP and LLM workflows, including orchestration and evaluation
- You use Git confidently in collaborative development and can design for long-term scale and maintainability
Who this fits
This role suits an engineer comfortable working across machine learning and backend development, contributing in Python and Go. The position is in Zagreb, Croatia. Expect a fast-moving startup setting where you may need to put in extra effort when needed and work independently while collaborating with a team.
From the employer
About ARTIDIS
Artidis is a pioneering clinical stage health technology company that aims to set the gold standard in tissue analysis and therapy optimization. By combining its nanotechnology platform for rapid tissue analysis with a holistic data solution, Artidis accelerates drug discovery, tissue engineering, and personalized treatment. Artidis focuses its research and development efforts on solid tumors to enhance responses to chemo, immuno, and cell therapies, driving precision in cancer care.
Job Purpose
As an AI Engineer NLP, you will design, develop, and deploy robust NLP systems for both medical devices and cloud environments. This role sits at the intersection of our NLP/ML team (Python) and platform/backend team (Go), requiring strong engineering capabilities across both domains to build scalable, production-grade AI systems.
Key Responsibilities
- Design, develop, and deploy agentic NLP systems and LLM-powered workflows across Python-based ML pipelines and Go-based backend services
- Act as a bridge between NLP and platform teams, translating ML requirements into scalable backend architectures and vice versa
- Contribute to both Python (ML/NLP) and Go (backend/platform) codebases, ensuring clean interfaces and efficient system integration
- Architect modular systems for LLM orchestration, APIs, and service communication (e.g., microservices, RPC, REST)
- Ensure reliability, performance, and compliance of AI systems in regulated medical environments
- Implement evaluation, monitoring, and observability across the full stack (model + service layer)
- Collaborate cross-functionally to deliver end-to-end AI-powered features from research to production
Core Qualifications
- Strong Python engineering skills, including:
- Advanced OOP, design patterns, and SOLID principles
- Experience with type-safe development (type hints, mypy, pydantic)
- Writing tested, maintainable, and production-grade code
- Experience building and deploying LLM/NLP systems in production (e.g., LangChain, Google ADK, HuggingFace)
- Experience or strong proficiency in backend development with Go, including API/service design
- Strong understanding of modern NLP/LLM workflows, including orchestration and evaluation
- Being native with Git version control and collaborative development workflows
- Ability to design systems with long-term scalability and maintainability in mind
Nice to Have
- Experience in backend, frontend, or full-stack development beyond core responsibilities
What We Value
- Ability to operate effectively across ML and backend engineering domains
- Engineering rigor applied to machine learning systems
- Clean, readable, and scalable code across languages
- Ownership mindset and proactive problem solving
- Ability to work independently while contributing to a collaborative environment
Working Conditions
The environment is a typical start-up with an intrinsically motivated international team. Our company is an excellent place for rapid advancement and offers a promising opportunity to learn and share know-how in a very agile environment. The position requires the employee to go the extra mile when needed. We are looking for a team player who appreciates direct communication. The effort is rewarded with challenging tasks, the opportunity to take responsibility, a highly driven team, and work that serves a significant purpose. The job position comes with a competitive salary and a bonus for outstanding performance.