AI Engineer 2

As an AI Engineer, you will develop the automation systems that power Hexalog's AI platform. Building on the foundational automation workflows created by the team, you will architect more complex multi-step systems that coordinate LLM reasoning, browser automation, document intelligence, and workflow orchestration. You will be responsible not only for building automation agents, but for designing the systems that allow them to operate reliably in production, including orchestration logic, evaluation frameworks, and observability pipelines. You will also collaborate with other AI and backend engineers and help them to build automation tools into scalable platforms. This role sits at the intersection of: LLM systems, Workflow Orchestration, and Automation Infrastructure.

Responsibilities: • Automation platforms that execute complex operational workflows across multiple business verticals. • Multi-agent automation systems that interact with external software through browser automation, APIs, and document intelligence pipelines. • Workflow orchestration frameworks that coordinate multi-step automation pipelines across agents, services, and human-in-the-loop escalation paths. • Evaluation and observability systems that measure LLM reasoning quality, extraction accuracy, and end-to-end workflow reliability. • Backend services and data pipelines that maintain system state and ensure reliable execution of automation workflows in production. • Foundations for scalable internal automation systems that will evolve into reusable platforms across the company.

Requirements: • 3-5 years of experience building distributed backend systems or AI-driven platforms in production. • Strong proficiency in Python, Typescript and experience designing and shipping production backend services or APIs (FastAPI or similar frameworks). • Experience designing or operating workflow orchestration systems such as Temporal, Airflow or similar platforms used to coordinate complex automation pipelines. • Familiarity with event-driven architectures that react to asynchronous events across services. • Experience working with LLM APIs, MCPs and modern AI and agentic coding tools. • Experience with Infrastructure as Code and cloud-native systems used to deploy AI workloads. • Working knowledge of modern cloud infrastructure, such as AWS Lambda, Fargate, or similar serverless and container execution environments. • Ability to reason about system reliability, failure modes, and debugging for AI-driven workflows. • A strong sense of curiosity and the ability to solve problems without a predefined playbook. • Comfort operating in ambiguous environments where ownership, experimentation, and rapid iteration are expected.