Senior AI Engineer – Python, RAG, Agentic AI, ADK, MCP, GCP, Vertex AI, IBM Watsox

Summary: Design, develop, and deploy cutting-edge AI systems leveraging Large Language Models, RAG, and agentic AI architectures. The role involves hands-on development with LLMs, embeddings, and multi-agent systems using modern frameworks like LangChain and Vertex AI on GCP.

Before you apply to a job, select your language preference from the options available at the top right of this page.

Explore your next opportunity at a Fortune Global 500 organization. Envision innovative possibilities, experience our rewarding culture, and work with talented teams that help you become better every day. We know what it takes to lead UPS into tomorrow—people with a unique combination of skill + passion. If you have the qualities and drive to lead yourself or teams, there are roles ready to cultivate your skills and take you to the next level.

Job Description:

Job Summary

We are seeking a highly skilled AI Engineer experience in Software Development, Data Science, or Machine Learning to design, develop, and deploy cutting-edge AI systems leveraging Large Language Models (LLMs), Chatbots, Retrieval-Augmented Generation (RAG), and agentic AI architectures.

This role involves hands-on development with LLMs, embeddings, RAG pipelines, and multi-agent systems using modern frameworks like LangChain, LangGraph, and LlamaIndex. The ideal candidate has experience with Vertex AI on GCP and IBM WatsonX, fine-tuning, and Agent Development Kits (ADKs), and is excited about building scalable, production-grade AI platforms.

Responsibilities

• Agentic AI Development:

Design, build, and deploy agentic AI systems using frameworks such as LangChain, LangGraph, and related libraries.

Develop and deploy multi-agent systems capable of autonomous decision-making, reasoning, planning, and collaboration.

• RAG Pipelines:

Implement and optimize retrieval-augmented generation (RAG) systems, ensuring agents can access and incorporate external knowledge sources for grounded, accurate responses.

• LLM Engineering:

Fine-tune and prompt-engineer LLMs for task-specific reasoning, planning, and dynamic adaptation.

Work with LLM/SLM APIs, embeddings, and advanced generative AI techniques.

• Enterprise AI Platform:

Lead the development of enterprise-grade AI platforms integrating LLMs, RAG, embeddings, and agentic AI protocols.

Implement and standardize Model Context Protocol (MCP) for consistent context management across models and agents.

• MLOps & Observability:

Establish and enforce best practices for MLOps, monitoring, and observability, ensuring scalable and maintainable AI solutions.

• Applied AI Prototyping:

Rapidly prototype, experiment, and iterate to improve AI agent capabilities.

• Collaboration & Research:

Participate in the full research cycle: literature review, data exploration, experimentation, and presentation of findings.

Collaborate effectively with other engineers, researchers, and data scientists.

Contribute to the documentation and standardization of technical code and practices.

Required Education

Bachelor’s degree in Computer Science, Engineering, or a related quantitative field. Master’s or Ph.D. is a strong plus.

Required Experience

• Relevant experience

Senior – Min 5+ yrs of relevance experience

Intermediate – Min 3+ yrs of relevance experience

Associate – Min 2+ yrs of relevant experience

• 1+ year of hands-on experience developing AI applications with LLMs and systems such as retrieval-based methods, fine-tuning, or agent-based architectures.
• 1+ year of experience with frameworks like LangChain, LlamaIndex, OpenAI, or similar tools.

Required Technical Skills

• Strong programming skills in Python and basics in SQL.
• Expertise with LLM/SLM APIs, embeddings, and RAG systems.
• Experience deploying on Google Cloud Platform (GCP) with Vertex AI, and IBM WatsonX.
• Familiarity with agentic AI protocols and exposure to Agent Development Kits (ADKs).

Preferred Qualifications

• Experience implementing Model Context Protocol (MCP) for agent coordination.
• Prior exposure to Lang Graph, AutoGen, or related orchestration frameworks.
• Knowledge of MLOps best practices (CI/CD for ML, observability, monitoring, scaling).
• Familiarity with responsible AI principles (safety, fairness, interpretability).
• Experience in enterprise-scale deployments of AI-driven platforms.
• Contributions to open-source AI/ML projects are a plus.

Employee Type:

Permanent

UPS is committed to providing a workplace free of discrimination, harassment, and retaliation.