Sr.Engineer

About Us:

As a Fortune 50 company with more than 400,000 team members worldwide, Target is an iconic brand and one of America's leading retailers.

Joining Target means promoting a culture of mutual care and respect and striving to make the most meaningful and positive impact. Becoming a Target team member means joining a community that values different voices and lifts each other up. Here, we believe your unique perspective is important, and you'll build relationships by being authentic and respectful.

Team Overview:

The Thinktank Agent Platform Team is building Target’s enterprise platform for developing, evaluating, deploying, and operating intelligent AI agents at scale. The platform provides reusable capabilities for agent orchestration, tool integration, evaluation, observability, governance, and optimization, enabling teams across Target to build reliable and secure agentic solutions.

The platform empowers engineering and product teams to rapidly create, test, monitor, and scale GenAI-powered agents while meeting enterprise standards for security, reliability, governance, and operational excellence.

Position Overview:

As a Senior Engineer on the Thinktank Agent Platform Team, you will design and build core platform capabilities that support agent development, orchestration, evaluation, observability, and production execution. You will work at the intersection of distributed systems, platform engineering, and GenAI to create reliable, scalable, and enterprise-grade agentic solutions.

Key Responsibilities

• Design and develop scalable backend and platform services for agent orchestration, execution, evaluation, and monitoring
• Build reusable capabilities for agent lifecycle management, tool integration, prompt and model configuration, and workflow execution
• Integrate LLMs, AI agents, enterprise tools, and external systems into production-grade solutions with strong reliability and guardrails
• Develop APIs, SDKs, and platform services that enable teams to build, test, deploy, and manage intelligent agents
• Build and enhance evaluation capabilities, including offline and online evaluations, test suites, quality metrics, and agent optimization
• Develop observability capabilities for tracing, monitoring, dashboards, alerts, and debugging agent behavior
• Ensure platform capabilities meet enterprise standards for security, governance, privacy, reliability, and auditability
• Collaborate with product, data science, application engineering, and enterprise architecture teams to define and deliver platform features
• Optimize system performance, scalability, resiliency, and cost efficiency in a cloud-native environment
• Contribute to engineering standards and best practices for building GenAI and agentic systems

Required Qualifications

• Bachelor’s or Master’s degree in Computer Science or a related field
• 4+ years of experience in backend, platform, or distributed systems engineering
• Strong programming skills in Java, Kotlin, Go or Python
• Experience building scalable distributed systems, APIs, and microservices architectures
• Familiarity with REST APIs, event-driven systems, asynchronous processing, and cloud-native technologies
• Understanding of system design, scalability, reliability, security, and observability principles
• Experience with containers, Kubernetes, CI/CD pipelines, and modern software delivery practices
• Experience working in agile, cross-functional engineering teams

Preferred Qualifications

• Experience with AI/ML or GenAI systems, including LLM integrations and agent-based applications
• Familiarity with agent orchestration frameworks, tool calling, prompt management, and multi-agent systems
• Experience building evaluation frameworks for LLMs or AI agents
• Knowledge of tracing, observability, monitoring, dashboards, and alerting for distributed or AI systems
• Experience developing platform APIs, SDKs, or reusable developer tools
• Understanding of AI safety, governance, guardrails, and responsible AI practices
• Experience with vector databases, retrieval-augmented generation, model gateways, or semantic search
• Frontend experience with React is a plus
• Experience with cloud platforms, GCP, AWS or Azure