Job Description

This is a remote position. We are looking for an AI Engineer to join our team and play a key role in designing, developing, and operating modern AI-powered applications. In this role, you will work across the full lifecycle of AI initiatives, building production-grade LLM services, intelligent retrieval systems, and agent-based solutions. You will collaborate closely with engineering and architecture teams to deliver reliable, secure, and scalable AI capabilities that create real business value. The role combines software engineering, AI engineering, and LLMOps expertise, with a strong focus on Generative AI, RAG architectures, and production-ready AI systems. Responsibilities Design, develop, and maintain AI services and APIs using: Python Django FastAPI Build and optimize end-to-end RAG (Retrieval-Augmented Generation) solutions, including: Chunking Embeddings Hybrid retrieval Reranking Vector database integration Design and implement agent-based solutions using modern orchestration frameworks Develop and maintain MCP-enabled tools and agent workflows Ensure AI solution quality through: Tracing and observability Evaluation frameworks Cost and token monitoring Performance optimization Write clean, tested, and well-documented code Participate in code reviews and engineering best practices Collaborate with multidisciplinary teams to deliver scalable AI solutions Contribute to knowledge sharing and technical documentation initiatives Requirements Strong proficiency in: Python Django FastAPI Experience with: PostgreSQL Redis Celery Docker Proven experience building and deploying production-grade RAG solutions Hands-on experience with: Embeddings Vector databases Retrieval systems Reranking techniques Experience with agent orchestration frameworks such as: LangGraph Haystack Google ADK Similar ecosystems Knowledge of: Prompt Engineering Model Context Protocol (MCP) Tool calling architectures Strong understanding of LLMOps practices, including: Observability Evaluation methodologies Cost optimization Latency management Streaming responses Experience with: OpenAPI Pytest Database migrations GitLab CI/CD Strong software engineering principles and testing practices Ability to work autonomously in collaborative environments Fluency in English Nice-to-have Experience with: Langfuse LLM evaluation frameworks LLM-as-a-Judge methodologies Experience designing reusable AI platforms and services Familiarity with modern Python tooling: uv ruff Experience working in product-focused or SaaS environments Strong documentation and knowledge-transfer capabilities If this sounds like you, share your CV with us and let’s talk!