Senior AI Engineer

Key Responsibilities

• Design, build, and operate AI systems for internal functions — agents, assistants, and automations — owning them end-to-end from design through production operation.
• Build the shared foundations of the crew's platform: frameworks, knowledge-base pipelines, evaluation tooling, and reusable integrations with company systems.
• Work directly with functional champions to understand their workflows, identify high-leverage automation opportunities, and turn them into deployed solutions.
• Implement security guardrails and responsible-AI practices in everything shipped: access control, data privacy, auditability, and human-in-the-loop where it matters.
• Make systems measurable: instrument adoption, quality, cost, and time savings, and use the data to iterate.
• Keep owned systems reliable, observable, and maintainable - including production incident response and RCA.
• Contribute to the AI software factory for engineering: rules, skills, and agents that codify Kpler's engineering standards, and AI-assisted development practices across crews.
• Provide clarity through documentation, proposals, and runbooks; share knowledge across the crew and company.
• Mentor other engineers in the crew and contribute to hiring and onboarding.

Experience & Background

Essential:

• 5+ years of software engineering experience building and operating production systems end-to-end.
• Hands-on experience shipping LLM-powered features, agents, or AI tooling to production (not just prototypes).
• Strong integration experience: third-party SaaS APIs, internal services, data pipelines.
• Solid grounding in system design, APIs, databases, and application architecture.
• Experience working directly with non-technical stakeholders to shape and deliver solutions.
• Practical understanding of security and data-privacy constraints around AI systems.
• Strong programming in Python and/or TypeScript.
• LLM application engineering: model APIs, agent frameworks, prompt/context engineering, RAG and knowledge bases.
• API design and systems integration across multiple SaaS platforms and internal systems.
• Cloud environments (AWS preferred), CI/CD, containerisation.

Desirable:

• Experience with agent frameworks, MCP-style tool interfaces, or multi-agent systems.
• Experience with RAG/knowledge-base systems and LLM evaluation/observability tooling.
• Experience building internal tools, platform tooling, or developer-experience products.
• Cost optimization of LLM workloads.
• Full-stack experience for user-facing internal tooling.