Lead Engineer - Genai

Target Target · Retail · Brooklyn Park, MN +1

Lead Engineer for GenAI at Target, focusing on designing and implementing autonomous AI agents with multi-step reasoning, task planning, and tool usage. The role involves leading development of agent orchestration frameworks, applying LLMs, building evaluation systems, implementing safety mechanisms, and creating data pipelines for training and inference. It emphasizes productionizing GenAI capabilities and adopting emerging technologies within an enterprise retail context.

What you'd actually do

  1. Design and implement autonomous AI agents capable of multi-step reasoning, task planning, tool usage, memory/state management, and iterative execution.
  2. Lead development of multi-agent coordination frameworks, agent orchestration layers, workflow engines, and tool invocation pipelines.
  3. Apply hands-on expertise with LLMs (OpenAI, Anthropic, Llama, Gemini, etc.) including prompt engineering, model adaptation, and inference optimization.
  4. Build and operationalize evaluation systems to measure agent accuracy, robustness, cost efficiency, latency, and reliability.
  5. Implement safety and trust mechanisms including content filters, alignment techniques, hallucination mitigation, monitoring pipelines, and auditability.

Skills

Required

  • Java
  • Python
  • PostgreSQL
  • OpenSearch
  • Elasticsearch
  • Object Storage (S3/etc.)
  • modern LLM ecosystems (OpenAI, Anthropic, Llama, Gemini, etc.)
  • productionizing GenAI capabilities
  • emerging GenAI patterns, frameworks and use-cases
  • LangGraph / LangChain / Google GenAI, etc.
  • Context Engineering / RAG / Agentic AI
  • designing scalable, reliable systems with strong performance, cost, and operational health awareness
  • stakeholder communication
  • lead through influence across teams and partners
  • building highly scalable distributed systems
  • broad and deep expertise in multiple computer languages and frameworks (e.g., open source)
  • Designs, develops, and approves end-to-end functionality of a product line, platform, or infrastructure

Nice to have

  • planning algorithms (ReAct, Tree-of-Thought, HTN)
  • policy learning
  • reward modeling
  • agent performance optimization strategies

What the JD emphasized

  • autonomous AI agents capable of multi-step reasoning, task planning, tool usage, memory/state management, and iterative execution
  • multi-agent coordination frameworks, agent orchestration layers, workflow engines, and tool invocation pipelines
  • LLMs (OpenAI, Anthropic, Llama, Gemini, etc.) including prompt engineering, model adaptation, and inference optimization
  • evaluation systems to measure agent accuracy, robustness, cost efficiency, latency, and reliability
  • safety and trust mechanisms including content filters, alignment techniques, hallucination mitigation, monitoring pipelines, and auditability
  • data pipelines to support training and fine-tuning, synthetic data generation, feature stores, and real-time inference workflows
  • evaluate and adopt emerging technologies, execute research/proof-of-concepts, and establish scalable engineering patterns and best practices
  • productionizing GenAI capabilities
  • emerging GenAI patterns, frameworks and use-cases
  • LangGraph / LangChain / Google GenAI, etc.
  • Context Engineering / RAG / Agentic AI

Other signals

  • design and implement autonomous AI agents
  • multi-step reasoning
  • task planning
  • tool usage
  • memory/state management
  • iterative execution
  • multi-agent coordination frameworks
  • agent orchestration layers
  • workflow engines
  • tool invocation pipelines
  • LLMs (OpenAI, Anthropic, Llama, Gemini, etc.)
  • prompt engineering
  • model adaptation
  • inference optimization
  • evaluation systems to measure agent accuracy, robustness, cost efficiency, latency, and reliability
  • safety and trust mechanisms
  • content filters
  • alignment techniques
  • hallucination mitigation
  • monitoring pipelines
  • auditability
  • data pipelines to support training and fine-tuning
  • synthetic data generation
  • feature stores
  • real-time inference workflows
  • evaluate and adopt emerging technologies
  • execute research/proof-of-concepts
  • establish scalable engineering patterns and best practices
  • productionizing GenAI capabilities
  • emerging GenAI patterns, frameworks and use-cases
  • LangGraph / LangChain / Google GenAI
  • Context Engineering / RAG / Agentic AI