Senior AI/Python Developer

• Design, implement, and continuously optimize production-grade AI applications powered by LLMs, with a focus on accuracy, latency, and cost efficiency
• Architect and orchestrate end-to-end RAG pipelines — from document ingestion and chunking strategies to retrieval tuning and response evaluation — using frameworks such as LangChain, LlamaIndex, or DSPy
• Build robust, high-performance APIs and microservices using FastAPI, Django, or Flask, following REST and async design best practices
• Collaborate closely with backend and platform teams to seamlessly integrate AI services into scalable, cloud-native architectures on Azure
• Own the reliability, observability, and performance of AI services in production — including monitoring, alerting, and iterative improvements based on real usage data
• Write clean, modular, and well-tested code with a strong emphasis on reusability and maintainability; actively contribute to internal standards and documentation
• Design and manage containerized deployments using Docker and orchestration tools (Kubernetes, Docker Compose), ensuring reproducibility across environments
• Drive technical discussions, architecture decisions, and code reviews — sharing knowledge and raising the bar for the entire team
• Evaluate and integrate emerging AI tooling, models, and techniques to keep the team at the cutting edge

• Strong Python proficiency with deep, hands-on engineering skills — from clean API design to production-grade ML pipelines
• Solid experience designing and deploying RAG-based systems and LLM-powered applications, including retrieval tuning, chunking strategies, embedding selection, and response evaluation using frameworks like LangChain or Semantic Kernel
• Practical knowledge of OpenAI, Azure OpenAI, and Amazon Bedrock APIs, combined with the ability to evaluate and route across models depending on cost, latency, and task requirements
• Experience architecting multi-cloud AI solutions with a strong emphasis on Azure (Azure ML, Azure AI Foundry, ADF) and familiarity with AWS counterparts — able to reason about trade-offs across cloud providers
• Hands-on experience running and orchestrating self-hosted LLMs — including model selection, quantization, serving (e.g. NVIDIA Triton, BentoML, vLLM), and lifecycle management in GPU-accelerated environments
• Familiarity with Transformer architectures at a non-superficial level — understanding of attention mechanisms, fine-tuning strategies, ViT/BERT variants, and their practical implications for production deployments
• Experience building production-ready AI applications using AI templates and scaffolding patterns (LLM app templates, prompt management, LLMOps tooling like ZenML, MLflow, or ArgoCD) — not just prototypes, but observable, maintainable systems
• Backend development experience with FastAPI, Django, or Flask, including async patterns and integration with AI services in microservice architectures
• Solid grasp of Docker and container orchestration (Kubernetes, Docker Compose) for reproducible model and service deployments

• Participation in interesting and demanding projects
• Flexible working hours
• A great, non-corporate atmosphere
• Stable employment conditions (contract of employment or B2B contract)
• Opportunities for development and promotion
• Attractive package of benefits
• Work model: remote or hybrid (2 days per week from the office)

We reserve the right to contact the selected candidates.