Senior AI Engineer

Role overview

Responsibilities

• check_circle Architect, develop, and deploy production-grade LLM capabilities within the Kayzen Console
• check_circle Build backend services, APIs, and integrations that connect AI capabilities with our product.
• check_circle Contribute to product-facing and full-stack functionality where needed.
• check_circle Implement production patterns for LLMs, RAG, embeddings, agents, and tool calling.
• check_circle Build reusable components and abstractions where they improve engineering velocity and consistency.
• check_circle Set up and improve evaluation, observability, monitoring, and feedback loops for AI features.
• check_circle Monitor and optimize quality, latency, reliability, and inference cost.
• check_circle Troubleshoot production issues and iterate based on telemetry and user feedback.
• check_circle Work closely with Product, ML and Engineering to translate product problems into pragmatic AI solutions.
• check_circle Prototype quickly, validate ideas, and turn successful experiments into maintainable production systems.

Basic qualifications

• Hands-on experience building and shipping LLM-powered features to production.
• Experience with LLM APIs and orchestration patterns; specific frameworks are less important than strong fundamentals.
• Good understanding of production LLM concerns such as evaluation, observability, failure modes, cost and latency.
• Experience iterating on AI features based on telemetry, evaluation results or user feedback.
• Full-stack product development using Angular, JavaScript/TypeScript, Python, NodeJS etc. is a strong plus.
• Strong experience designing APIs, services and production-grade systems.
• Ability to write clean, maintainable code and take ownership from implementation through production.
• Experience contributing across a product stack and willingness to work on both backend systems and user-facing product functionality.
• Comfort working with AWS cloud infrastructure, CI/CD and production environments.
• Bias for shipping, iteration and pragmatic problem solving.
• Comfortable with ambiguity and rapid change.
• Able to collaborate closely with Product, ML and Engineering stakeholders.
• Can discuss trade-offs, challenge requirements constructively and translate AI complexity into practical product solutions.
• Thinks in terms of maintainability and reuse rather than one-off demos.
• Heavy model training or research.
• Designing custom ML algorithms.
• Academic optimization work.
• Building proofs of concept that never reach production.

Preferred qualifications

• Experience with multi-agent systems, tool calling or MCP.
• Experience setting up guardrails, moderation and safety checks.
• Experience with prompt/context management, routing, caching or fallback strategies.
• Experience with Docker and cloud infrastructure (AWS, GCP or Azure).
• Experience with modern frontend development and customer-facing web applications.
• Direct access to top management and an extremely "visible" role
• Exceptional career growth and learning opportunity
• A unique opportunity to be part of an experienced team of industry experts and entrepreneurs who bring massive change to the Adtech market
• A fun, driven, and multinational team located across Germany, India, UK, Argentina, Ukraine, Turkey, Spain and many more countries
• A flexible work-from-home arrangement
• A 500-dollar home-office setup budget
• A 1000-dollar annual learning and development budget
• Visa and relocation support (if required)