Eurisko is looking for an AI Engineer to build and deploy applications using Large Language Models (LLMs) and Generative AI.
You will work with AI leads, product teams, and software engineers to develop intelligent features, connect models to enterprise systems, and improve the quality and performance of AI applications in production.
What you’ll do
- Develop and integrate LLM-powered features, including AI assistants, knowledge search, document processing, and workflow automation.
- Build and improve Retrieval-Augmented Generation (RAG) pipelines, covering data ingestion, chunking, embeddings, vector search, and retrieval.
- Develop and maintain prompts, AI workflows, tool integrations, and connections to external APIs and business systems.
- Write clean, maintainable, and tested Python code for AI services and backend integrations.
- Build evaluation tests, investigate incorrect outputs, and improve response quality, latency, and cost.
- Implement data privacy controls, access restrictions, and safeguards for reliable AI behavior.
- Collaborate with backend, data, QA, and DevOps teams to deploy, monitor, and support AI features.
- Participate in Agile/Scrum ceremonies, including planning, estimation, daily stand-ups, and sprint reviews.
What you’ll bring
- Practical experience developing LLM and GenAI applications, with examples of solutions you have built or contributed to.
- Strong Python skills and solid software engineering fundamentals.
- Experience with prompt engineering, RAG, embeddings, and vector databases or vector search.
- Experience integrating LLM APIs or working with open-source language models.
- Familiarity with REST APIs, Git, automated testing, and debugging.
- Understanding of AI evaluation, hallucinations, context limitations, and secure handling of sensitive data.
- Experience working in Agile/Scrum teams.
- Strong problem-solving skills, attention to quality, and the ability to collaborate across disciplines.
Nice to have
- Experience in banking, fintech, or financial services.
- Experience with microservices architecture and integrating AI services into distributed applications.
- Familiarity with frameworks such as LangChain or LangGraph, including agent workflows and tool calling.
- Experience with cloud platforms, Docker, and CI/CD.
- Exposure to model fine-tuning, multimodal AI, or deploying open-source models.
