Lead Engineer - Modernization Team

Target Target · Retail · NCD-0375 Brooklyn Park, MN

Lead Engineer for the Target Technology Modernization team, focused on transforming legacy systems using Generative AI, LLMs, and prompt engineering. Responsibilities include application architecture, driving architectural changes, evaluating new technologies, leading research and proof-of-concept activities, and implementing scalable software solutions. Requires hands-on experience with LLM ecosystems, GenAI patterns, and frameworks like LangGraph/LangChain, with a focus on RAG and Agentic AI.

What you'd actually do

  1. Use your technology acumen to apply and maintain knowledge of current and emerging technologies within specialized area(s) of the technology domain.
  2. Evaluate new technologies and participates in decision-making, accounting for several factors such as viability within Target’s technical environment, maintainability, and cost of ownership.
  3. Initiate and execute research and proof-of-concept activities for new technologies.
  4. Lead or set strategy for testing and debugging at the platform or enterprise level.
  5. In complex and unstructured situations, serve as an expert resource to create and improve standards and best practices to ensure high-performance, scalable, repeatable, and secure deliverables.

Skills

Required

  • Java
  • Python
  • modern LLM ecosystems (OpenAI, Anthropic, Llama, Gemini, etc.)
  • productionizing GenAI capabilities
  • PostgreSQL
  • Open/Elasticsearch
  • Object Storage (S3/etc.)
  • LangGraph / LangChain / Google GenAI, etc
  • Context Engineering / RAG / Agentic AI

Nice to have

  • Generative AI platforms
  • large language model (LLM) techniques
  • prompt engineering
  • code generation
  • model adaptation
  • inference optimization

What the JD emphasized

  • modernize software development
  • productionizing GenAI capabilities
  • emerging GenAI patterns, frameworks and use-cases

Other signals

  • Generative AI platforms
  • large language model (LLM) techniques
  • prompt engineering
  • code generation
  • model adaptation
  • inference optimization
  • modernize software development
  • research, experimentation, and iterative development
  • modern LLM ecosystems
  • productionizing GenAI capabilities
  • emerging GenAI patterns, frameworks and use-cases
  • LangGraph / LangChain / Google GenAI
  • Context Engineering / RAG / Agentic AI