AI-engineer

Team: AI

Location: Belgrade

Commitment: Full-Time

Workplace Type: onsite

What You'll Be Doing:

• At Unlimit, AI isn’t a side project – it’s core to how we operate and innovate. As an AI Engineer, your day-to-day won’t be about just tuning models or writing scripts in isolation. You’ll be building real-world systems that make decisions, automate complex workflows, and empower teams across the company.
• You’ll start by diving deep into our operations – identifying high-impact opportunities where automation can replace repetitive processes. You’ll design and implement orchestrated workflows that tie together APIs, databases, and AI models, with monitoring baked in from day one so we trust what we deploy.
• You’ll also get your hands dirty developing conversational agents and intelligent bots that do more than just answer questions – they take actions, understand nuance, and support our teams across compliance, support, and product development. Some of these agents will live in Slack, others on the web, and some will integrate with tools we haven’t adopted yet – you’ll shape that roadmap.
• Much of your work will touch on retrieval-augmented generation (RAG) pipelines. You’ll implement vector search solutions, blending large language models with live business data so our systems always have the right context at the right time. You’ll experiment with prompt engineering strategies – from chain-of-thought to few-shot – running automated evaluations to see what truly moves the needle.
• And this isn’t a solo mission. You’ll collaborate closely with Legal, AML, DevOps, QA, and product teams – translating complex needs into AI-powered solutions that respect governance and deliver measurable value. You won’t just be building models. You’ll be helping us build trust in the decisions those models make.

Qualifications You Bring:

• Must-Have:
• Bachelor’s or Master’s degree in Computer Science, Engineering, or related field.
• At least 3 years of hands-on experience in AI/ML engineering or automation.
• Strong experience using LangChain/LangGraph for building LLM applications.
• Deep knowledge of vector databases (FAISS, PGVector, Qdrant) and RAG architectures.Proficiency in Python, FastAPI, and key ML frameworks (Transformers, PyTorch, TensorFlow).Proven ability in advanced prompt engineering techniques.


• Nice-to-Have:
• Familiarity with n8n or similar workflow orchestration platforms.
• Experience deploying and managing production-scale LLMs (AWS SageMaker, Azure ML, Hugging Face).
• Practical fine-tuning skills (LoRA, full-model fine-tuning, hyperparameter optimization).
• Experience with containerization (Docker) and orchestration systems (Kubernetes).
• Solid understanding of MLOps and LLMOps tools and practices (MLFlow, Grafana, Prometheus).


If you’re passionate about crafting impactful AI solutions that revolutionize business processes, we’d love to meet you!