Data engineer in AI applications

At Synechron, we harness the power of digital transformation to drive business success. As a global consulting firm, we combine creativity with advanced technology to deliver innovative solutions across industries. Recognized with multiple employer awards, we are committed to building talented teams and creating a dynamic work environment. As a Data Engineer, you will design and build scalable data using Python, FastAPI, Azure OpenAI, and modern LLM frameworks. You will work across API development, RAG pipelines, semantic search, AI agents, and cloud-based data services, helping deliver reliable, production-ready AI applications.

• Design, develop, and maintain Python-based data and AI applications, including REST APIs using FastAPI.
• Build and optimize LLM applications, RAG pipelines, semantic search solutions, and AI agents using LangChain and LangGraph.
• Integrate Azure OpenAI and OpenAI APIs, working with GPT-4 and GPT-5 models, embeddings, vector databases, and Azure data services.
• Develop efficient SQL and NoSQL queries and work with Azure Blob Storage and Azure Databases.
• Evaluate, test, troubleshoot, deploy, and monitor AI models and applications to ensure quality, reliability, and performance.
• Collaborate with engineering and product teams and contribute to clean code, Git/GitHub workflows, CI/CD, and technical documentation.

• 5–8 years of professional experience in data engineering, software engineering, or a related role.
• Strong Python development skills and hands-on experience with FastAPI and REST API development.
• Strong SQL and NoSQL query writing skills.
• Hands-on experience with Azure OpenAI, OpenAI APIs, Generative AI, and GPT-4/GPT-5.
• Experience building LLM applications, RAG pipelines, AI agents, and agentic AI solutions.
• Practical experience with LangChain, LangGraph, vector databases, embeddings, vector search, and semantic search.
• Experience with Azure Blob Storage, Azure Databases, Git, and GitHub.
• Experience with AI model evaluation, testing, troubleshooting, deployment, monitoring, and observability.
• One of the prerequisites for this position is that the prospective candidate must possess a valid work permit for Serbia.
• Будет плюсом: Experience with Flask or Django, Knowledge Graphs, Ontology concepts, and Semantic Layers; Exposure to MLOps and LLMOps practices and frameworks; Knowledge of Elasticsearch, Kafka, and Redis; Experience with Docker, Kubernetes, CI/CD pipelines, Azure DevOps, or GitHub Actions; Exposure to AWS or GCP cloud services; Experience developing conversational AI or Copilot solutions

• Compensation package based on experience and skills
• Flexible hours and hybrid work options, allowing you to achieve a work-life balance that suits your needs
• Private health insurance plan
• Access to continuous training, accredited certifications, access to unlimited Udemy courses and a range of resources to help you grow professionally
• Personalized leadership training program
• FitPass membership to support your well-being and mental health support programs
• Comprehensive Referral Rewards Program