We are looking for a Machine Learning Engineer to help us deploy, configure, and optimize Mistral 7B, integrate it into our services, and implement Retrieval-Augmented Generation (RAG) for database interactions.
Key Responsibilities:
- Configure and optimize Mistral 7B for business tasks (fine-tuning, quantization, performance optimization).
- Assess required computational resources, select the optimal infrastructure for model deployment (on-premise or cloud), and analyze cost efficiency.
- Implement RAG to integrate models with vector databases.
- Orchestrate interactions between multiple ML services (e.g., one model generates tags, and another validates task descriptions).
- Develop a service for interacting with the model (API for predictions, model management, integration with our application).
- Optimize model performance for real-world usage.
Requirements:
- Experience with LLM models (Mistral 7B, GPT-3/4, LLaMA, Claude, Falcon, Bloom, etc.).
- Understanding of Retrieval-Augmented Generation (RAG) and model integration with databases.
- Hands-on experience with fine-tuning and dataset preparation/annotation.
- Experience with vector databases (Pinecone, Weaviate, FAISS).
- Strong proficiency in Python and libraries like PyTorch, TensorFlow, Hugging Face, and LangChain.
- Experience in evaluating and optimizing infrastructure for AI deployments.
- Experience in developing APIs for integrating AI models into business processes.
We offer:
- Comfortable working hours (10-19 Kyiv time zone);
- Regular result-based salary reviews;
- Bonus system tied to the product’s success;
- Established product-focused environment;
- Range of tasks, from quick and simple to challenging investigation to run;
- Cheerful & dynamic environment;
- Friendly and open-minded team;
- Virtual workspace with perspective to move into one of the offices;
- Mentorship;
- Gym and English classes discounts.
Hiring steps:
- 1st interview with the Recruiter;
- Technical interview with the Squad Lead;
- Job offer.