About this Staff AI Software Engineer role at Entrata
Responsibilities
Define technical strategy and architecture for large-scale LLM, agent, retrieval, and AI platforms at the company level.
Establish reusable patterns for agent graphs, MCPs, orchestration, state management, memory, context engineering, tool use, and multi-agent systems.
Define standards for prompting, model selection, routing, structured outputs, guardrails, and failure recovery.
Design strategies for memory, personalization, conversation history, summarization, retrieval, and data retention across AI systems.
Establish model-selection frameworks that balance quality, latency, cost, context requirements, safety, and reliability.
Lead the design and adoption of AWS AI capabilities, including Amazon Bedrock and AgentCore.
Define evaluation methodologies and quality standards for AI systems, including offline evaluations, online metrics, human review, regression testing, and production feedback loops.
Establish observability standards for agent traces, tool calls, state transitions, memory access, model behavior, latency, cost, and failures.
Drive technical decisions related to reliability, security, privacy, governance, performance, and responsible AI.
Investigate complex AI failures and distinguish model limitations from issues in prompting, orchestration, memory, retrieval, tooling, or application design.
Build reusable AI platforms, frameworks, and engineering practices that enable software engineers to develop AI applications effectively.
Identify high-leverage opportunities to apply AI to customer and business problems.
Influence product and engineering roadmaps through deep technical expertise and business context.
Mentor AI engineers and software engineers working on AI-enabled products.
Resolve ambiguous, high-risk technical challenges and unblock multiple teams.
Communicate AI architecture, tradeoffs, limitations, and technical strategy clearly to engineering and business stakeholders.
Qualifications
6+ years of experience in software engineering or related fields, including 4+ years with AI, data science, or related technologies.
Expert proficiency in Python or a similar programming language.
Strong working knowledge of Node.js and JavaScript or TypeScript.
Demonstrated experience defining and scaling production AI or generative AI systems across multiple teams or products.
Deep expertise in LLM behavior, agent architecture, prompting, context engineering, state management, memory, tool use, retrieval, and model evaluation.
Experience designing agentic platforms, orchestration frameworks, or multi-agent systems.
Strong experience with AWS AI services, including Amazon Bedrock, AgentCore, or equivalent platforms.
Deep understanding of AI evaluation, observability, safety, reliability, governance, and responsible AI.
Strong background in distributed systems, backend architecture, cloud platforms, and production operations.
Ability to diagnose complex AI behavior using experiments, traces, evaluations, and production data.
Experience creating reusable AI frameworks and standards that allow other engineers to build safely and effectively.
Experience influencing technical strategy across multiple teams or product areas.
Proven ability to lead through ambiguity, make sound tradeoffs, and deliver measurable outcomes.
Exceptional communication, mentoring, and stakeholder-management skills.