Senior Agentic AI Engineer

Boeing Boeing · Aerospace · Bangalore, India, India

Senior Agentic AI Engineer at Boeing responsible for developing and deploying AI agents that leverage retrieval-augmented generation (RAG) and enterprise data for decision-making and workflows. The role involves collaborating with stakeholders, designing retrieval strategies, developing ML models, and ensuring data security and compliance.

What you'd actually do

  1. Decompose complex problems into manageable tasks and develop end-to-end data-driven solutions architect that include modeling, retrieval, and integration into workflows, leading the way from capabilities to solutioning
  2. Design and optimize retrieval-augmented generation (RAG) patterns that support agent workflows and decision-making.
  3. Define retrieval strategies for enterprise content sources, structured data, unstructured documents, and operational systems.
  4. Evaluate retrieval performance, relevance, latency, and answer fidelity across use cases.
  5. Create testing and benchmarking approaches for retrieval quality and downstream agent outcomes.

Skills

Required

  • Experience working with stakeholders to create data science problem statements from vague business requirements
  • Natural language processing (NLP) techniques (tokenization, embedding generation, summarization, named entity extraction, etc.)
  • Large language models and their applications in retrieval-augmented generation and agent workflows
  • Machine learning regression and multi-class classification models, especially under imbalanced data conditions
  • RAG architectures and retrieval systems in production or enterprise environments
  • How LLMs use retrieved context within agent workflows
  • Retrieval concepts such as chunking, embeddings, vector search, metadata filtering, hybrid retrieval, reranking, and query rewriting
  • Evaluate retrieval quality and answer grounding for accuracy and relevance
  • Analytical and problem-solving skills
  • Written and verbal communication skills
  • Ability to work effectively across development, data, product, and governance teams
  • Data access controls, privacy, and security considerations
  • Proficiency working with configuration and data formats such as Python, JSON, and YAML

What the JD emphasized

  • retrieval-augmented generation (RAG)
  • agentic AI workflows
  • retrieval strategies
  • enterprise data
  • securely and effectively use enterprise data
  • retrieval systems
  • agent workflows
  • retrieval quality
  • data access controls, privacy, and security considerations

Other signals

  • Develops and deploys AI agents
  • Focuses on RAG and retrieval strategies
  • Integrates AI solutions into enterprise workflows