AI Engineer II - Python,AWS

Position Overview:

We are seeking a talented and driven AI Engineer to join our growing team at Diligent. Reporting to the Engineering Manager, this role involves bridging the gap between Applied Scientists, the AI Central team, and Product Engineering teams — designing, developing, deploying, and scaling production-grade ML and LLM-based systems as part of Diligent’s AI platform services. This role focuses on taking real customer and governance use cases from idea to measurable impact, accelerating AI adoption across Diligent's diverse product suite.

Diligent is a global leader in modern governance, delivering innovative SaaS solutions that address governance, risk, and compliance (GRC) needs. Our mission is to empower leaders with cutting-edge technology, actionable insights, and vital connections to drive impactful decisions and lead with purpose.

Key Responsibilities:

• Design, develop, deploy, monitor, scale, and troubleshoot production ML and LLM-based systems that power services across Diligent’s AI platform.

• Take ownership of AI features end-to-end — from problem definition and design through implementation, deployment, monitoring, and iteration.

• Collaborate closely with Applied Scientists, the AI Central team, and Software Engineers to fast-track implementation and productization of AI capabilities.

• Build automated AI testing, evaluation, and quality frameworks, including prompt evaluation and model performance tracking.

• Shape and evolve the team’s AI platform infrastructure using established organizational patterns and infrastructure-as-code practices.

• Design and develop reusable AI libraries, patterns, prompts, and frameworks to accelerate value delivery across teams.

• Add logging, metrics, and quality evaluation from day one to ensure AI systems are observable, reliable, and measurable.

• Work on projects involving sensitive customer and board-level content, requiring stringent privacy, security, and compliance controls.

• Design guardrails to mitigate hallucinations, misuse, and data leakage in AI systems.

• Document and communicate technical designs, trade-offs, progress, and outcomes to the broader team and partner development groups.

• Enable other engineers and QAs to effectively use AI tools by sharing best practices and mentoring on AI-augmented workflows.

Required experience/skills:

• 3+ years of experience building and operating production software systems (beyond POCs or experiments).

• Strong engineering foundations with the ability to write clean, readable, well-tested Python code that adheres to SOLID principles.

• Hands-on experience with LLMs, including prompt engineering, embeddings, Retrieval-Augmented Generation (RAG), and evaluation techniques.

• Solid experience with AWS, including infrastructure-as-code practices (CDK, Terraform, or similar).

• Ability to own features end-to-end and operate AI systems in production environments.

• Strong product and problem-solving mindset, starting from real customer, RTB, or process problems.

• Experience scoping small, high-impact POCs and iterating quickly toward measurable outcomes (e.g., time saved, defects reduced, efficiency gains).

• Ability to contribute to a high-performing agile team, collaborate cross-functionally, and continuously improve processes.

• Keen to share knowledge, patterns, and best practices to act as an AI multiplier for the broader team.

Nice to have:

• Hands-on AWS CDK experience.

• Experience with Amazon Bedrock.

• Experience with agentic workflows, orchestration frameworks, or MCP-style servers.

• Experience across the full AI solution lifecycle, from experimentation to long-term production operation.