Engineer 2, AI Agentic Solutions

As a Software Engineer II on the Enterprise AI team, you will serve as a lead individual contributor driving the technical vision, architecture, and production delivery of autonomous agentic systems. You are a product-minded engineer capable of translating complex, ambiguous business problems into scalable AI-driven solutions spanning multi-month roadmaps.

In this role, you will define agent user experiences, establish evaluation benchmarks, optimize token economics, and guide system design across cross-functional engineering, product, and security organizations., * Architect & Deploy Agentic Systems: Design, build, and maintain production-grade agent orchestration pipelines, structured tool-use integrations, and enterprise downstream system connectors.

• Context Engineering & Retrieval: Formulate context-window strategies balancing token economics, latency constraints, and response quality across RAG architectures, vector search, and dynamic prompt assembly.
• Evaluation, Observability & Guardrails: Build end-to-end evaluation frameworks, offline benchmark suites, automated safety guardrails, and real-time production telemetry to guarantee reliability, safety, and deterministic performance.
• State & Memory Management: Implement durable conversation states, dynamic working context, and long-term memory architectures across multi-session user journeys.
• Technical Trade-Offs & Cost Governance: Balance rapid delivery against long-term architectural scalability, factoring in foundation model selection, context caching, inference costs, and cloud infrastructure budgets.
• Technical Leadership & Quality Bar: Lead rigorous design and code reviews, establish enterprise AI coding standards, mentor junior engineers, and interview prospective technical candidates.
• Cross-Functional Collaboration: Partner closely with Product, Security, and Cloud Infrastructure teams to resolve architectural friction and align AI capabilities with corporate roadmaps.

• Bachelor’s degree in Computer Science, Computer Engineering, a related technical field, or equivalent practical experience.
• 6+ years of professional software engineering experience designing, building, and operating scalable backend services or distributed systems.
• Direct production experience building generative AI applications using foundation model APIs (e.g., OpenAI, Anthropic, Gemini), dynamic prompt engineering, and Retrieval-Augmented Generation (RAG).
• Proficiency in Python and cloud-native software development on AWS, Google Cloud Platform, or Azure.
• Practical experience implementing evaluation metrics, safety guardrails, and telemetry for production LLM systems., * Master’s degree in Computer Science, Artificial Intelligence, or a related quantitative field.
• Experience deploying agentic orchestration frameworks in production (e.g., LangGraph, AutoGen, CrewAI, Semantic Kernel, or Claude Agent SDK).
• Hands-on experience with multi-agent orchestration architectures, including task decomposition, tool routing, and human-in-the-loop workflows.
• Strong background in database engineering and distributed storage across relational SQL, NoSQL, and vector databases (e.g., Pinecone, Milvus, pgvector).
• Proven experience with containerization and orchestration tooling (Docker, Kubernetes) alongside automated CI/CD pipelines.
• Familiarity with enterprise-scale transactional domains, such as digital commerce, omnichannel retail, inventory supply chain, or customer workflow automation.
• Active contributions to open-source AI tooling or peer-reviewed research in applied LLM systems.