AI Engineer

Our client is a rapidly scaling, remote-first software provider specializing in governance technology. They streamline mission-critical decision-making and meeting workflows for high-level corporate leadership. Their diverse client base features leading European industrial groups, major media conglomerates, and energy giants, including several Tier-1 publicly traded corporations.

Tech stack: ASP.NET Core, React.js, F#, functional programming, event-driven architectures, AI, Azure.

Requirements

• AI & Agentic Frameworks: Proven experience building AI features into production SaaS products, including Agentic tools, RAG pipelines, and Model Context Protocol (MCP).
• Vector Infrastructure: Deep understanding of vector databases and semantic search optimization.
• Backend Engineering: Strong proficiency in ASP.NET Core and F# (or a deep commitment to Functional Programming paradigms).
• Architecture: Experience designing and maintaining scalable, event-driven architectures.
• Cloud Ecosystem: Hands-on experience with Azure deployments, specifically leveraging Azure AI infrastructure.
• Frontend Integration: Experience working with React.js to deliver seamless, intuitive AI-driven user experiences.

Nice to have:

• Familiarity with benchmarking and evaluating different LLM providers and models’ unique capabilities to optimize cost and latency.
• Experience with advanced prompt engineering, fine-tuning workflows, or guardrail implementation.
• Knowledge of modern CI/CD practices for AI/MLOps in an Azure environment.

Responsibilities:

• AI Feature Development: Design, build, and deploy production-grade AI capabilities into our SaaS product, utilizing RAG pipelines, autonomous agentic tools, and Model Context Protocol (MCP).
• Architectural Engineering: Architect and maintain highly scalable, reliable backend solutions using ASP.NET Core and F#, strictly adhering to functional programming principles and event-driven architectures.
• Vector & Data Management: Implement and optimize vector databases to ensure ultra-low latency, highly accurate semantic search and contextual data retrieval.
• Model Selection & Evaluation: Evaluate, benchmark, and integrate diverse LLMs and foundation models, matching their unique capabilities to specific product requirements for optimal cost, speed, and accuracy.
• Cloud & AI Infrastructure: Orchestrate and manage secure, scalable workloads within the Azure ecosystem, specifically leveraging Azure AI deployments.

Benefits

• Udemy courses of your choice
• Team-buildings, events, marathons & charity activities to connect and recharge
• Workshops, trainings, expert knowledge-sharing that keep you growing
• Clear career path
• Absence days for work-life balance
• Flexible hours & work setup — work from any of listed locations and organize your day your way

Відгукнутись на вакансію