Senior AI Engineer (LLM)

Tidio Poland is hiring a Senior AI Engineer to work on greenfield, high-scale, user-facing NLP and LLM systems with long-term ownership and impact. The role involves building and deploying production AI solutions, including LLM-powered applications, with a focus on scalability, performance, and reliability.

• At least 4 years of experience in ML / AI engineering
• Proven experience owning production NLP or LLM systems
• Strong understanding of scalability, performance, and system design
• Proven experience designing and deploying end-to-end NLP and deep learning solutions in production environments
• Hands-on experience building LLM-powered production systems (e.g., GPT, Claude, Gemini), including prompt engineering, evaluation, fine-tuning, and user-facing integrations
• Proficiency in Python with experience building and maintaining reliable production services and data pipelines
• Strong software engineering mindset, including code quality, testing, scalability, and production deployments
• Experience building RESTful APIs (FastAPI, Flask) to expose ML/LLM capabilities
• Curiosity and commitment to continuous learning in the NLP/LLM/AI space
• Collaborative team-player with strong communication skills

Nice to have:

• Experience with RAG
• Experience with PyTorch
• Experience with MLOps
• Experience with Hugging Face
• Experience with Flask

• Designing, implementing, and deploying end-to-end NLP and deep learning systems
• Building LLM-powered applications that interact with real users
• Developing and maintaining production Python services
• Exposing models and pipelines via REST APIs (FastAPI, Flask)
• Working on retrieval models and techniques (RAG, embeddings, ranking)
• Evaluating, monitoring, and continuously improving model and system quality
• Scaling systems to handle enormous volumes of requests

How this role works:

• Start by building the system as part of the team in a greenfield setup
• After a few months, continue working directly with the client on the same product
• No handover phase or context switching; long-term ownership of the codebase and product

Biggest challenges in this role:

• Greenfield project built from scratch
• High-scale, user-facing systems with strict performance and reliability requirements
• Designing systems for long-term ownership
• Balancing model quality, latency, and cost in production LLM systems

What you’ll get to try and experiment with:

• End-to-end ownership of LLM-based systems
• Optimizing retrieval models, RAG pipelines, and inference workflows
• Experimenting with different LLMs, prompting strategies, and system designs
• Solving performance and reliability challenges under heavy traffic