Senior AI Engineer

About the role

Arkham is a Data & AI platform that helps large enterprises unify fragmented systems and data, build a single source of trusted operational metrics and solve complex challenges with AI tailored to their operations. As a Senior AI Engineer, you build and own the systems that power AI at Arkham: the in-platform LLM application used by data and financial analysts at enterprise customers, and the internal agentic frameworks that support software engineers across the development lifecycle. You have end-to-end ownership, from system design and development through deployment, monitoring and continuous improvement.

Key responsibilities

• Build and evolve the in-platform LLM application so enterprise users can explore data, perform analysis and inform business decisions
• Develop internal agentic frameworks and tools supporting code development, testing, review and CI pipelines
• Design backend services, APIs and infrastructure that support AI applications and agent execution
• Build agentic workflows with tool integration, state management and failure recovery
• Set up evaluations and automated testing to measure quality and prevent regressions
• Own deployment, monitoring, debugging and ongoing improvement of production systems
• Improve reliability, latency and cost across models, tools and backend services
• Work with engineering and product to define technical approaches and establish reusable patterns for AI development

Required profile

• 3+ years of professional Python development, with a track record of shipping and maintaining production applications
• 2+ years designing and building backend systems, including APIs, databases and asynchronous workflows
• Strong software engineering fundamentals: testing, debugging, version control and code reviews
• Ability to own systems from technical design through deployment and production maintenance
• Ability to turn ambiguous requirements into practical technical decisions and working software
• Strong collaboration and communication skills, able to explain architectural decisions and their tradeoffs

Nice to have

• Hands-on experience with agentic workflows, tool calling, state management and failure recovery
• Experience integrating LLMs into applications, including structured outputs, context management and external tools or data sources
• Experience designing evaluations for AI system quality and catching regressions
• Experience with RAG, search and document processing
• Experience implementing permissions, data isolation and safeguards for AI systems that take actions
• Understanding of the tradeoffs between model quality, latency and cost
• Experience building developer tools or automating parts of the software development lifecycle