We are looking for a Senior AI Engineer to design and build production-grade AI applications and services using Python. In this role, you will turn business and AI use cases into reliable, scalable technical solutions, working with LLMs, backend services, APIs, and enterprise systems.
What You’ll Do
Design and build production-grade AI applications and services using Python
Translate business requirements and AI use cases into practical technical solutions
Build backend services, APIs, workflows, and integrations that incorporate LLMs and other AI capabilities
Design evaluation frameworks and test cases to measure the quality and reliability of AI outputs
Develop techniques to improve the consistency and predictability of LLM-powered features
Implement observability, instrumentation, tracing, and monitoring for AI systems
Build reusable components for prompting, model interaction, evaluation, retrieval, and orchestration
Develop automated tests and CI/CD pipelines for AI applications
Integrate AI applications with enterprise data platforms, APIs, and business systems
Diagnose and resolve issues in deployed applications and support production workloads
Contribute to architecture and technology decisions across AI products
Review engineering work and establish best practices for Python and AI application development
Work directly with clients and stakeholders to refine requirements, evaluate trade-offs, and shape solutions
What You Bring
Must-Haves
5+ years of experience in software engineering, backend engineering, applied AI, or related fields
Strong Python fundamentals and experience building maintainable, production-grade Python applications
Experience designing and deploying AI or LLM-powered products beyond proof-of-concept or notebook environments
Experience building backend services and APIs using Python
Strong understanding of software engineering fundamentals, including modular design, testing, version control, and CI/CD
Hands-on experience evaluating LLM outputs and designing repeatable test cases for AI applications
Experience with observability, instrumentation, logging, tracing, or monitoring of production applications
Understanding of the challenges involved in making probabilistic AI systems reliable and predictable
Experience integrating applications with external APIs, data sources, and enterprise systems
Ability to reason from first principles and solve unfamiliar technical problems rather than relying solely on frameworks or tools
Strong communication skills and experience working directly with technical and business stakeholders
Ability to balance hands-on delivery with technical guidance and solution design
Nice-to-Haves
Experience with RAG, semantic search, embeddings, vector databases, or other retrieval-based AI architectures
Experience building agentic or multi-step LLM workflows
Familiarity with structured LLM outputs, tool calling, and schema-driven application patterns
Experience with AI evaluation, experimentation, or observability platforms
Experience with Microsoft Azure AI Foundry, Microsoft Fabric, Databricks, or similar enterprise platforms
Experience with cloud infrastructure, containerisation, and production deployment of Python services
Familiarity with modern Python frameworks and tooling for APIs, data validation, testing, and dependency management
Experience integrating AI applications with enterprise data platforms and semantic layers
Exposure to consulting, financial services, manufacturing, or other enterprise environments
Experience supporting production applications used by external clients or business-critical teams
