AI Engineer

· Build end-to-end AI agents and workflow automations from initial use-case scoping through deployment and ongoing maintenance.

· Write production Python code to integrate LLM APIs (prompt construction, response handling, context management, tool use) into internal workflows.

· Integrate AI tools with existing enterprise systems (NetSuite, HubSpot, M365, ServiceNow, etc.) via APIs with proper logging and monitoring.

· Establish reusable code patterns and component libraries to accelerate future agent development.

· Develop evaluation harnesses and model pipelines (training, evaluation, deployment) using AIOps practices to automate quality scoring and regression detection.

· Own deployed agent operations, including identity management, performance monitoring, human reinforcement workflows, and failure triaging.

· Optimize inference performance and cost through caching, batching, quantization, model selection, and workload management.

· Partner with Data Engineers to define feature requirements and create high-quality training and validation datasets.

· Apply responsible AI controls (privacy, security, governance) and collaborate with Security/Compliance to meet regulatory expectations.

· Maintain technical documentation, runbooks, and operational procedures for production AI services.

· Communicate project status, outcomes, and technical complexities clearly to both technical and non-technical stakeholders.

Required Experience and Education

· Bachelor’s degree in Computer Science, Engineering, Data Science, or a related field, or equivalent work experience.

· Proven experience (5+ years) building production software systems, with at least 2+ years delivering AI/ML or GenAI solutions.

· Strong software engineering fundamentals (APIs, testing, CI/CD, observability) and proficiency in Python and/or another relevant language.

· Experience with ML frameworks and tooling (e.g., PyTorch/TensorFlow-like concepts) and/or GenAI stacks (LLM APIs, vector databases, orchestration).

· Knowledge of AIOps practices (model registry, experiment tracking, deployment strategies, monitoring) and responsible AI principles.

· Ability to communicate clearly with both technical and non-technical stakeholders; comfortable iterating quickly in ambiguous problem spaces.