Description
We are looking for an exceptional AI Engineer to contribute to the design and development of our advanced Agentic AI systems. In this role, you will work closely with a dedicated AI engineering team, leveraging cutting-edge LLMs and multi-agent frameworks to build intelligent, autonomous workflows that integrate seamlessly into our core platform.
Responsibilities
•Build, and deploy production-ready, multi-agent workflows using frameworks such as LangGraph and CrewAI in Python.
•Fine-tune, evaluate, and deploy both frontier LLMs (e.g., OpenAI, Anthropic) and open-source models (e.g., Llama, Mistral) tailored to specific domain tasks and datasets.
•Seamlessly integrate agentic systems into existing software infrastructure, ensuring high reliability, low latency, and scalable performance.
•Stay at the forefront of AI research and tooling, continuously evaluating new models, frameworks, and techniques to improve AI capabilities.
Requirements
•Minimum 5+ years of hands-on software and AI/ML engineering experience, with deep, production-level expertise in Python.
•Proven track record of designing and implementing complex AI agents and multi-agent systems using tools like LangGraph, CrewAI, or AutoGen.
•Strong practical experience prompting, fine-tuning, and evaluating Large Language Models (both proprietary/frontier and open-source).
•Ability to consistently overlap with the core team from 4:00 PM to 7:00 PM Belgrade time (CET/CEST).
Nice to have
•Hands-on experience deploying and managing AI models using AWS Bedrock and the broader AWS generative AI ecosystem.
•Experience operating within stringent security, governance, and compliance standards (e.g., banking or financial sectors).
•Background in building evaluation frameworks for LLM outputs (e.g., RAG metrics, hallucination detection).
Conditions
•Build real-world, production-facing agentic systems that solve complex, high-value problems.
•Fully remote setup with targeted, predictable overlap hours.
