Full Stack AI Application Engineer

eBay•Austin, TX
•Remote

About The Position

eBay is seeking a Full Stack AI Application Engineer to design and implement advanced agentic AI systems. The engineer will build production-ready AI agents capable of multi-step reasoning, using frameworks and pipelines that combine LLM-based reasoning, knowledge grounding, and multi-agent orchestration. The role partners with product and engineering teams to turn workflows into reliable, scalable agentic solutions for real-world use cases. The position involves developing agentic systems with retrieval-augmented generation (RAG) and integrations to tools, databases, and APIs; backend services and MCP tool connectivity; document classification, routing, OCR, and information extraction; and resilient asynchronous services and MLOps infrastructure. The engineer will deliver production-grade workflows on cloud platforms, monitor and evaluate performance, and continuously improve quality and efficiency. Systems must be scalable, performant, resilient, and meet availability targets of 99.99%.

Requirements

  • Proficiency developing backend services using Java, including Spring or Spring Boot.
  • Hands-on experience with multi-agent orchestration and supervisor patterns.
  • Knowledge of RAG pipelines, memory management, and evaluation of agent performance.
  • Hands-on experience with OCR systems, layout analysis, or vision-language models applied to document extraction.
  • Experience designing custom evaluation metrics for reasoning steps, tool-use correctness, and RAG pipeline performance.
  • Ability to balance automatic evaluation with human-in-the-loop evaluation for complex workflows.
  • Experience with agentic architecture, including agent frameworks, tool-calling protocols, and planning/execution patterns.
  • Knowledge of reinforcement learning, planning algorithms, or autonomous reasoning.
  • At least 6 years of hands-on experience developing RESTful APIs, microservices, and Kubernetes operators, emphasizing testability, scalability, and maintainability.
  • Proven experience leading and contributing hands-on to AI/ML engineering and operations in large-scale production environments.

Responsibilities

  • Build multi-step reasoning agents, RAG systems, and integrations with tools, databases, and APIs.
  • Develop backend services and API integrations, including connectivity to MCP tools.
  • Build or fine-tune multimodal and vision-language classification models, or use vision LLMs and embeddings, to identify document categories and detect page-level anomalies.
  • Integrate and benchmark OCR engines to extract information from complex layouts, tables, and handwritten or printed text.
  • Deploy models and pipeline workers as resilient asynchronous microservices, with latency, throughput, and privacy safeguards such as PII masking and encryption in transit and at rest.
  • Deliver production-grade agentic AI workflows on cloud platforms, monitor and evaluate agent performance, and continuously fine-tune systems for quality and efficiency.
  • Develop and maintain scalable, efficient, performant, and resilient capabilities that meet 99.99% availability targets.
  • Contribute hands-on to AI/ML engineering and operations in large-scale production environments.

Benefits

  • Target bonus and restricted stock units, as applicable.
  • Medical benefits.
  • Financial benefits.
  • 401(k) eligibility.
  • Paid time off, including PTO and parental leave.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service