Senior AI Engineer
RemoteSerbia
Job Summary
Design and implement end-to-end LLM-powered applications, focusing on Retrieval-Augmented Generation (RAG) pipelines and scalable vector database architectures. Build production-ready AI systems using Python and modern frameworks, optimizing data ingestion, embedding pipelines, and semantic search workflows. Integrate selected AI platforms and APIs, then deploy and maintain solutions in cloud environments like AWS, Azure, or GCP. Collaborate cross-functionally with product and engineering teams to translate business requirements into robust technical solutions while ensuring code quality, testing, and performance optimization. Contribute to MLOps practices including CI/CD pipelines, model lifecycle management, and observability.
Required Qualifications
- Master's degree in Computer Science, Engineering, AI, or a related field
- 7+ years of experience in backend software engineering with the latest 1-2 years developing and implementing AI-powered solutions
- Proven hands-on experience building and deploying LLM applications, especially RAG-based systems
- Strong programming skills with the following order of preference regarding languages: Python > .NET > TypeScript > Java
- Experience integrating LLM APIs (e.g., OpenAI, Anthropic, Azure OpenAI)
- Solid understanding of vector databases (e.g., Pinecone or Weaviate) and semantic search architectures
- Experience with at least one major cloud platform (AWS, Azure, or GCP) in production environments
- Understanding of APIs, microservices, and scalable backend architecture
- Experience deploying applications to production environments
- Strong problem-solving skills and ability to work in a fast-evolving AI landscape
Desired Qualifications
- Experience contributing to AI system architecture design and technical standards
- Experience participating in AI roadmap discussions and technical planning
- Experience designing or implementing multi-agent AI systems
- Experience with alternative vector databases (e.g., FAISS, Milvus)
- Experience with Hugging Face ecosystem or fine-tuning open-source models
- Hands-on experience with advanced MLOps frameworks and model governance
- PhD (completed or in progress) in a relevant field
- Experience mentoring junior engineers or leading smaller technical initiatives
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.