Ai Software Engineer

Lever, Inc.; United States; On-site; USD 120,000 - 180,000; Full time

Job summary

Entrata seeks an AI Software Engineer to build and operate production-grade LLM and agent systems. You will design agent graphs, prompts, and memory strategies, and integrate AWS Bedrock into scalable workflows. Collaborate with product and data science teams to deliver reliable AI features.

You will work on retrieval, grounding, evaluation, and observability, ensuring secure and efficient AI-driven functionality across the platform.

Qualifications

• 1–4 years in software engineering or related fields; 2+ years with AI or data science technologies.
• Strong proficiency in Python, JavaScript, or TypeScript.
• Proven experience building and operating LLM or agentic systems in production.
• Deep understanding of prompting, tool calling, structured outputs, and memory management.
• Experience designing agent graphs, multi-step workflows, and failure-handling behavior.
• Experience evaluating models for task-specific performance, latency, cost, and reliability.

Responsibilities

• Build, deliver, and maintain production-grade LLM, agent, retrieval, and ML workflows.
• Design and maintain agent graphs, states, routing, and tool integrations.
• Develop prompting strategies, response schemas, and guardrails for multi-agent systems.
• Configure memory, context, and privacy boundaries for context handling.
• Select and configure models based on task requirements and constraints.
• Integrate AWS AI services (Bedrock) and platform capabilities into AI systems.
• Design robust retrieval/grounding strategies and evaluation suites.
• Investigate unexpected agent behavior using traces and production data.

Skills

Python

JavaScript/TypeScript

LLM/agent systems

Prompting & structured outputs

Memory management

Model evaluation & grounding

System design & ownership

Tools

Node.js

Amazon Bedrock

AgentCore

CI/CD

Cloud platforms

Job description

Since 2003, Entrata has evolved from a visionary, student-led startup into a global leader in AI-driven property management technology. Today, we power the industry's most essential operating system, serving owners and residents worldwide through a comprehensive suite of intelligent leasing, payment, and communication tools powered by cutting-edge AI. With a proven track record of sustained growth and a global team of more than 2,200 employees, we offer the rare combination of established stability and high-velocity innovation. Recognized by the Silicon Slopes Hall of Fame and the Utah Business Fast 50, Entrata fosters a culture of radical transparency and entrepreneurial energy. At Entrata, we create an environment where different perspectives are valued and respected. Those perspectives challenge assumptions, strengthen our decisions, and raise the bar as we reshape the global living experience through AI-powered solutions.

Responsibilities

• Systems & Workflow Delivery: Build, deliver, and maintain production-grade LLM, agent, retrieval, and machine-learning workflows, product platforms, and features using structured orchestration patterns.

• Agent Architecture & Orchestration: Design, define, and maintain agent graphs, MCPs, states, transitions, routing logic, retries, fallbacks, escalation behavior, and tool integrations using established patterns.

• Prompt Engineering & Structured Outputs: Develop and refine comprehensive prompting strategies across system prompts, task prompts, tool instructions, response schemas, guardrails, and multi-agent interactions.

• Memory & Context Management: Configure and design short-term state, long-term memory, conversation history, summarization, retrieval, and privacy boundaries to determine how context is retained, retrieved, or excluded.

• Model Selection & Configuration: Select and configure appropriate models based on task requirements, capability, latency, cost, context length, operational constraints, and reliability.

• AWS & Platform Integration: Use AWS AI services and platform capabilities—such as Amazon Bedrock and AgentCore—to build, deploy, and operate AI systems, integrating agents with tools, APIs, databases, and existing application services.

• Retrieval & Grounding Strategies: Design robust retrieval and grounding strategies, including chunking, embeddings, ranking, metadata, filtering, and source attribution.

• Evaluations & Testing: Create, run, and scale quantitative/qualitative evaluation suites that measure correctness, completeness, reasoning, safety, tool use, latency, grounding, and regression detection.

• Debugging, Diagnostics & Observability: Investigate and analyze unexpected agent behavior, evaluation results, and production traces to diagnose whether failures originate in the model, prompt, state, memory, retrieval, tools, or application code. Establish monitoring and observability for AI behavior.

• Project Ownership & Technical Leadership: Own AI projects from technical design through production deployment and ongoing improvement. Define reusable patterns and libraries that allow software engineers to build on the company's AI harness safely and consistently.

• Software Development & Standards: Develop, test, debug, and maintain supporting application code and backend services while applying high standards for security, privacy, testing, and responsible AI.

• Collaboration & Guidance: Collaborate closely with product, design, data science, and engineering partners to translate ambiguous problems into reliable AI capabilities, providing technical guidance and code reviews for engineers building AI-enabled features.

Qualifications

• 1–4 years of experience in software engineering or related fields, including 2+ years with AI, data science, or related technologies.

• Strong proficiency in Python, JavaScript, TypeScript, or a similar programming language.

• Strong working knowledge of Node.js and JavaScript or TypeScript.

• Demonstrated experience building and operating LLM or agentic systems in production.

• Strong understanding of prompting, tool calling, structured outputs, agent orchestration, state management, context construction, and memory.

• Experience designing agent graphs, multi-step workflows, routing strategies, and failure-handling behavior.

• Experience selecting and evaluating models for different tasks and understanding quality, latency, cost, and reliability tradeoffs.

• Practical experience with Amazon Bedrock, AgentCore, or equivalent cloud AI services.

• Experience with RAG systems, vector databases, embeddings, ranking, and grounding techniques.

• Experience building quantitative and qualitative evaluations for LLM and agent behavior.

• Experience using traces, logs, production data, and evaluation results to diagnose AI system failures.

• Strong understanding of MCPs, APIs, distributed services, databases, cloud platforms, containers, CI/CD, and observability.

• Strong system design, communication, ownership, and collaboration skills.

Entrata is dedicated to creating a workplace where a diverse and inclusive team thrives in an environment free from discrimination. We provide equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, protected veteran status, or any other applicable characteristics protected by law.

It’s a great place to work! Will you join us?