Responsibilities
โ LLM configuration and optimization (Mistral, LLaMa, Qwen or others) โ fine-tuning, quantization, performance tuning;
โ Assessing required computational resources, selecting the optimal infrastructure for model deployment (on-premise or cloud), and analyzing cost efficiency;
โ Implementing RAG to integrate models with vector databases;
โ Orchestrating interactions between multiple ML services (e.g., one model generates tags, and another validates task descriptions).
โ Developing a service for interacting with the model (API for predictions, model management, integration with our application).
โ Optimizing model performance for real-world usage.
Requirements
โ 1+ years experience with LLM models (Mistral 7B, GPT-3/4, LLaMA, Claude, Falcon, Bloom, etc.);
โ Understanding of Retrieval-Augmented Generation (RAG) and model integration with databases;
โ Proficiency in Python and libraries like PyTorch, TensorFlow, Hugging Face, and LangChain;
โ Experience in evaluating and optimizing infrastructure for AI deployments;
โ Experience in developing APIs for integrating AI models into business processes;
โ English level at least A2-B1.
Nice To Have
โ Hands-on experience with fine-tuning and dataset preparation/annotation;;
โ Experience with vector databases (Pinecone, Weaviate, FAISS);
โ Experience with Java.
We Offer
โ Regular result-based salary reviews;
โ Comfortable working hours (10-19 Kyiv time zone);
โ Bonus system;
โ Established product-focused environment;
โ Range of tasks, from quick and simple to challenging investigation to run;
โ Cheerful & dynamic environment;
โ Friendly and open-minded team;
โ Virtual workspace with perspective to move into one of the offices;
โ Mentorship;
โ Attractive social package (unlimited and paid sick days, fully paid vacation, birthday day off, etc;)
โ Sport and English classes discounts.
Hiring Steps
โ First interview with the Recruiter;
โ Technical interview with the Team Lead;
โ Job Offer.
English: B1
Experience: 1 year
Work location: Remote
Office: Prague, CZ
Work type: Full-time
Apply now