Senior AI Engineer_ (Backend)

Role Description
Senior AI Engineer (Backend)
Experience: 8-12 Years
AI Engineer – Production AI Agents
About The Team And The Role
Global Consumer Insights (GCI) sits within eBays Growth organization and ignites growth by
bringing the voice of the consumer into client most important decisions. As AI-enabled tools
become central to how insights are created, synthesized, and activated, GCI is investing in
responsible, practical capabilities that help researchers and business partners move faster, work
smarter, and deliver greater impact.
As an AI Engineer focused on Production AI Agents, you will partner closely with Product,
Research, Engineering, and cross-functional stakeholders to design, build, and scale
AI-powered systems that enhance how insights are generated and operationalized. This role
emphasizes moving beyond experimentation to deliver reliable, evaluation-driven AI solutions
that integrate seamlessly into real workflows. You will play a key role in shaping GCIs AI
ecosystem by building robust agent architectures, ensuring production readiness, and
continuously improving system performance and trust.
What You Will Accomplish

• Design and build stateful, multi-agent AI systems using modern orchestration
  

frameworks, enabling scalable and reliable workflows for insights generation and
synthesis.

• Collaborate with Product, Research, and business stakeholders to translate
  

requirements into end-to-end AI solutions, from proof of concept through evaluation
and production deployment.

• Solid understanding of Retrieval-Augmented Generation (RAG), including hybrid
  

search, re-ranking, and advanced retrieval techniques.

• Implement evaluation frameworks and pipelines (e.g., LLM-as-a-Judge, automated
  

benchmarks) to measure system performance, reliability, and quality before and after
release.

• Develop and maintain scalable backend services for high-throughput, low-latency
  

workloads, while contributing to lightweight frontend components to deliver functional
prototypes and internal tools.

• Optimize batching, streaming, caching, and request orchestration in distributed and
  

async environments.

• Improve production systems across latency, throughput, reliability, observability, and unit
  

economics.

• Partner with infrastructure teams to leverage GPU-enabled and cloud-native
  

environments effectively.

• Establish monitoring, tracing, and observability practices for complex AI systems,
  

ensuring performance, reliability, and debuggability in production.

• Develop reusable platform components, MCPs / APIs, and best practices for AI
  

application development.

• Drive a pragmatic, evaluation-driven approach to adopting new AI technologies,
  

balancing innovation with reliability and business impact.

• Stay current with advancements in AI (e.g., reasoning models, SLMs, prompting
  

strategies) and apply them to improve systems and workflows.

• Partner with cross-functional teams to ensure AI solutions align with responsible AI,
  

privacy, and security standards.
What You Will Bring

• 8 to 12 years of experience in software engineering, AI/ML engineering, or full-stack
  

development, with hands-on ownership of building and deploying production-grade
applications or platforms.

• 4+ years of focused experience building and deploying AI-centric systems.
• 2+ years of hands-on experience with LLM-based agents, autonomous workflows, or
  

multi-agent orchestration.

• Strong full-stack engineering experience, with deep expertise in Python and familiarity
  

with TypeScript or Node.js.

• Hands-on experience with AI orchestration frameworks such as LangGraph,
  

LlamaIndex Workflows, or similar tools.

• Solid understanding of Retrieval-Augmented Generation (RAG), including hybrid
  

search, re-ranking, and advanced retrieval techniques.

• Experience implementing observability and tracing for AI systems (e.g., LangSmith,
  

LangFuse, Arize Phoenix).

• Production experience with modern ML tooling and frameworks (for example: PyTorch,
  

Transformers, scikit-learn).

• Proven experience taking AI-powered products from prototype to production with strong
  

maintainability and operational quality.

• Proven ability to design and execute evaluation pipelines and testing frameworks to
  

ensure reliability and reduce hallucinations.

• Experience working with APIs/SDKs from major model providers (OpenAI, Anthropic,
  

Gemini) and open-source models.

• Experience deploying and managing services on cloud platforms (AWS, Azure, or
  

GCP) and using containerization (Docker/Kubernetes).

• Familiarity with CI/CD pipelines and DevOps practices.
• Strong collaboration and communication skills, with the ability to work effectively across
  

technical and non-technical teams.
Preferred Qualifications

• Experience with Spring-based service development.
• Familiarity with big data and processing ecosystems (for example: Spark, Hadoop).
• Experience with streaming systems (for example: Kafka, Flink, Beam).
• Experience with RAG pipelines, vector stores, tool-use frameworks, and multimodal
  

model integration.

• Exposure to GPU optimization and performance tuning (for example: CUDA, inference
  

optimization techniques).

• Experience building conversational AI systems (intents, entities, dialog flows, and
  

interaction design).

• Familiarity with prompt optimization tools such as DSPy.
• Proficiency with vector databases (Pinecone, Weaviate, Qdrant, pgvector).
• Exposure to voice agents or multimodal AI systems.
• Experience with graph databases (e.g., Neo4j) or GraphRAG approaches.
• Foundational knowledge of machine learning or model fine-tunin