AI / LLM Engineer

What you'll do

• Design and build LLM-powered applications using OpenAI, Anthropic, Llama, and similar models
• Build and optimize RAG pipelines with vector databases (Pinecone, Weaviate, pgvector)
• Develop agentic AI systems with orchestration frameworks like LangChain, LlamaIndex, CrewAI
• Implement MLOps / LLMOps practices for model deployment, monitoring, and evaluation
• Collaborate with clients and engineers to define AI architecture and strategy
• Conduct AI red-teaming and output validation

Requirements

• 2+ years of experience in software engineering with Python
• Hands-on experience with LLM APIs (OpenAI, Anthropic, or open-weight models)
• Experience with RAG architectures and vector search
• Understanding of prompt engineering and context management
• Familiarity with ML concepts and model evaluation
• Strong written and spoken English

Nice to have

• Experience with LangChain, LlamaIndex, or similar frameworks
• Experience with MLflow, Weights & Biases, or similar MLOps tools
• Knowledge of fine-tuning techniques (LoRA, QLoRA)
• Experience with cloud platforms (AWS, Azure, GCP)
• Contributions to open-source AI projects

As part of our team you'll enjoy

• Work on real production AI projects, not demos
• Fully remote with access to offices in Belgrade
• Competitive salary
• Flexible vacation & paid time off
• Health insurance
• Weekly AI research sessions with the team
• Access to premium AI tools and compute resources

Other open positions