AI Engineer

Grant Thornton is building an AI Factory to deliver enterprise‑grade, agentic AI solutions that move beyond pilots into sustained business impact. As an AI Engineer, you will be a core builder within a cross‑functional AI Pod, responsible for implementing, testing, and deploying agentic systems into real client workflows. This role is hands‑on and execution‑focused. You will turn architectural designs and product intent into reliable, observable, and production‑ready AI components, working closely with the AI Product Lead, Lead AI Architect, and Automation Engineers.

Responsibilities

Agentic System Development

• Build and implement agentic AI components, including:
• Tool‑using agents
• Multi‑step reasoning and execution flows
• Planner, executor, and validator agent patterns
• Translate architectural designs into working, maintainable code
• Ensure agent behavior is bounded, predictable, and aligned with intent

• Develop prompts as versioned, testable software artifacts
• Implement and tune:
• Retrieval‑augmented generation (RAG)
• Memory and context‑management strategies
• Input and output constraints
• Optimize prompts and retrieval for accuracy, latency, and cost

• Build evaluation harnesses to assess:
• Accuracy and relevance
• Hallucination and failure rates
• Regression across prompt and model changes
• Implement automated testing and validation for AI workflows
• Partner with the Lead AI Architect to monitor drift and degradation over time

• Package and deploy AI components into production environments
• Integrate AI logic into APIs, services, and workflows
• Instrument solutions for:
• Performance
• Usage
• Cost‑to‑serve
• Support production troubleshooting and iterative optimization

• Work closely with:
• AI Product Lead to align implementation with acceptance criteria
• Lead AI Architect on design decisions and patterns
• Automation / Integration Engineers to enable real‑world execution
• Contribute to reusable components, templates, and patterns within the AI Factory

• English - Spanish Language (Oral and writing B2+ or above).
• Bachelor’s degree in computer science, Engineering, or a related field is desirable.
• Minimum of 5 years of experience in AI, automation, or a related field.
• Proficiency in UiPath and MS Power Automate, or similar automation platforms.
• Strong understanding of UiPath architecture and its components, with experience in server administration (Windows and Linux) and cloud environments (Azure, AWS).
• Proficiency with cloud platforms such as AWS, Azure, or GCP, particularly for deploying and managing UiPath Orchestrators.
• Experience with data analysis and reporting tools like MS Power BI.
• Experience with database management (SQL Server, Oracle).
• UiPath Certified Professional Advanced RPA Developer (UiARD) Certification is required. Additional certifications in cloud platforms (AWS, Azure) are highly desirable.
• Strong leadership abilities with a focus on mentoring junior engineers.
• Excellent analytical, problem-solving, and troubleshooting skills.
• Collaborative mindset with the ability to work effectively across cross-functional teams.
• Adaptability to changing circumstances, learning new technologies, and driving continuous improvement.
• High integrity and ethical standards in professional conduct.

About Auxis

• 4–8+ years of experience in software engineering, data engineering, or applied AI development
• Hands‑on experience building and deploying systems into production environments
• Comfort working in agile, fast‑moving delivery teams

• Practical experience with:
• Generative AI and LLMs
• Agentic frameworks or orchestration patterns
• Tool calling and action execution
• Strong understanding of common LLM failure modes and mitigation techniques
• Ability to reason about when to rely on AI vs deterministic logic

• Strong proficiency in Python
• Experience with:
• API development and integration
• Event‑driven or workflow‑based systems
• CI/CD and modern DevOps practices
• Familiarity with cloud‑native architectures (Azure preferred)

• Experience implementing:
• Retrieval‑augmented generation (RAG)
• Vector databases and embedding strategies
• Exposure to monitoring, observability, or MLOps concepts
• Experience working in enterprise or regulated environments
• Consulting or client‑facing delivery experience