AI Engineer (GenAI / Agentic Platform)

Who you are

This is the right role for you if you:

• Are an engineer who enjoys building real-world AI products and platforms, not just experimenting with models. You are comfortable working in a fast-moving environment where technologies, patterns, and best practices are still evolving. You take ownership, make pragmatic decisions, and help translate AI potential into secure, scalable, and business-relevant solutions.
• Have a genuine passion for Generative AI and Agentic AI. You stay up to date with advancements in the field, enjoy exploring new approaches, and have strong opinions backed by hands-on experience. At the same time, you understand that successful AI solutions require much more than model selection: engineering quality, observability, security, and user adoption are equally important.
• Care deeply about software craftsmanship. Clean architecture, maintainable code, automated testing, and operational excellence are part of how you work. You also enjoy collaborating with others, sharing knowledge, and contributing to a culture of continuous learning and innovation.

Your background and skills include:

• 5+ years of software engineering experience, including designing, building and operating production-grade applications in cloud environments.
• Proven hands-on experience delivering Generative AI solutions, including LLM-powered applications, Retrieval-Augmented Generation (RAG), tool/function calling and agent-based workflows in production environments.
• Strong Python skills and solid experience building APIs, integrations, and backend services that interact with enterprise platforms and data sources.
• Deep understanding of RAG architectures, including document ingestion, chunking strategies, embeddings, retrieval optimization, grounding techniques, vector search and evaluation methodologies.
• Experience with agentic AI frameworks and orchestration patterns, such as LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI, or equivalent technologies.
• Experience building cloud-native AI solutions, preferably on Google Cloud Platform (GCP), including Vertex AI, model serving, vector search services, containerized applications and CI/CD automation.
• Experience building observable and reliable AI systems, including automated evaluations, monitoring, telemetry, tracing, guardrails, and performance optimization.
• Strong understanding of software engineering best practices, including testing strategies, security principles, scalability and maintainability.

It would be ideal if you also:

• Have experience building or contributing to enterprise AI platforms supporting multiple teams and business domains.
• Have hands-on experience with Snowflake, including integration of AI capabilities with enterprise data platforms.
• Are familiar with the Model Context Protocol (MCP) and standards for AI agent interoperability.
• Have experience working with foundation models such as Claude (Anthropic), OpenAI GPT models, Gemini, or open-source LLMs.
• Have experience implementing Responsible AI, governance, security and compliance controls in regulated environments.
• Have worked within financial services, banking, risk, regulatory reporting, or data-intensive enterprise environments.

If this sounds like you, get in touch!

Next steps

​Submit your application no later than 11/11/2026.

The recruitment process consists of the following steps:

• Preliminary CV selection
• Online interview with the hiring leader
• Background check