Senior AI Engineer

Are you passionate about AI?

At Satori Analytics, we aim to change the world one algorithm at a time by bringing clarity to global brands through Data & AI. From cloud-based ecosystems for fintech to predictive models for airlines, our cutting-edge solutions cover the entire data lifecycle—from ingestion to AI applications.

As a fast-growing scale-up, our team of 100+ tech specialists—including Data Engineers, Data Scientists, and more—delivers innovative analytics solutions across industries like FMCG, retail, manufacturing and FSI. Join us as we lead the data revolution in South-Eastern Europe and beyond!

We are looking for a Senior AI Engineer who can bridge the gap between modern Generative AI capabilities and robust Software Engineering. You will design and build scalable AI-powered applications, work with Large Language Models and agentic systems, and help turn rapidly evolving GenAI technologies into reliable, maintainable products.

What Your Day Might Look Like:

• Build production-grade GenAI applications: Design and develop AI-powered services and applications using Python, LLMs and modern software engineering practices—from prototypes to scalable production systems.
• Engineer intelligent workflows: Build RAG pipelines, AI agents, tool-calling workflows, structured generation, conversational systems and other LLM-powered capabilities that solve real business problems.
• Own the software behind the AI: Develop clean, modular and testable backend services, APIs and integrations, ensuring AI solutions are scalable, maintainable and production-ready.
• Design AI architectures: Make architectural decisions around model selection, orchestration, retrieval, APIs, caching, data stores, vector databases and cloud infrastructure.
• Make AI reliable: Implement evaluation frameworks, observability, tracing, monitoring and guardrails to understand how AI systems behave and continuously improve their quality.
• Optimize performance: Improve latency, throughput, reliability and cost across LLM-powered applications through model routing, caching, asynchronous processing and thoughtful system design.
• Integrate the AI ecosystem: Work with foundation models and platforms from providers such as OpenAI, Anthropic, Google, Microsoft and open-source ecosystems.
• Collaborate across disciplines: Work closely with Software Engineers, Data Engineers, Data Scientists, Product teams and domain experts to translate business requirements into effective AI products.
• Lead technically: Guide engineering decisions, review designs and code, mentor other engineers and establish best practices for building GenAI applications.
• Stay ahead: Explore emerging GenAI technologies, frameworks and architectural patterns and assess where they can create meaningful value rather than adopting technology for technology's sake.
• Document and share: Create clear technical documentation, architectural decisions and reusable patterns that help the broader team build better AI systems.

Your Superpowers:

• Degree in Computer Science, Software Engineering, STEM or equivalent practical experience.
• 5+ years of professional software engineering experience, ideally building backend, cloud-native or data-intensive applications, including 1+ year in building GenAI systems.
• Strong experience designing and developing production systems using Python.
• Solid understanding of software engineering fundamentals, including clean architecture, design patterns, testing, API design, concurrency, asynchronous programming and maintainable codebases.
• Hands-on experience building applications with Large Language Models and Generative AI, including areas such as:
• Retrieval-Augmented Generation (RAG)
• Agentic workflows and tool/function calling
• Αgent orchestration, multi-agent systems, MCP or tool-based AI architectures.
• Prompt engineering and structured outputs
• Embeddings and semantic search
• Context and conversation management
• LLM evaluation and observability
• Guardrails and responsible AI patterns
• Experience with frameworks and libraries such as FastAPI, Pydantic and at least one GenAI orchestration ecosystem such as LangChain, LangGraph, LlamaIndex or Semantic Kernel.
• Experience working with mainstream AI platforms and foundation models from OpenAI, Azure OpenAI, Anthropic, Google and/or open-source model providers.
• Experience with vector databases and search technologies, such as Azure AI Search, Elasticsearch/OpenSearch, pgvector, Pinecone, Weaviate, Qdrant or similar.
• Strong understanding of REST APIs, distributed systems and service-oriented architectures.
• Experience with Git, Docker and CI/CD practices.
• Hands-on experience with at least one major cloud platform such as Azure or AWS.
• Experience writing automated tests and building reliable engineering workflows.
• Ability to reason about trade-offs between model quality, latency, scalability, security and cost.
• Fluent English and strong communication skills, with the ability to explain complex technical decisions clearly to both technical and non-technical stakeholders.

Bonus Points for:

• Experience designing or operating LLM applications at scale in production.
• Experience with LLMOps / GenAIOps, including evaluation pipelines, tracing, prompt/version management, monitoring and experimentation.
• Experience with Kubernetes, serverless architectures or event-driven systems.
• Experience with frontend technologies such as React or TypeScript and an interest in building complete AI-powered products.
• Experience integrating GenAI applications with enterprise data sources, authentication systems and business applications.
• Experience with AI security concepts such as prompt injection mitigation, data access controls, PII handling and secure tool execution.
• Familiarity with open-source LLMs, model serving, inference optimization or fine-tuning techniques.
• Previous experience mentoring engineers or acting as a technical lead.

Perks on Perks:

• Competitive salary and hybrid work model – come hang out in our Athens office or work remotely from anywhere in European economic Area (EU, Switzerland etc.) or UK (up to 6 weeks per year).
• Training budget to level up your skills from the top tech partners in the market (Microsoft, AWS, Salesforce, Databricks etc.) – whether it’s certifications or courses, we’ve got you covered.
• Private insurance, top-tier tech gear, and the chance to work with a stellar crew.

Ready to create some data magic with us? Hit that apply button and let’s get started.