Applied AI Engineer
Location: Bellevue, WA (Seattle area preferred)Compensation: $150,000-$300,000 DOE + equityTeam Size: 6
About the Company
Our client is a well-funded, early-stage startup building an AI-first enterprise automation platform where intelligent agents resolve operational tasks autonomously, learn from outcomes, and continuously improve over time.This is an opportunity to join as an early Applied AI Engineer and own a significant portion of the agentic AI stack from day one. You'll help shape both the technical direction and engineering culture while working alongside a highly experienced founding team.
The Role
You'll design and build the core AI agent framework powering an autonomous enterprise execution platform. This role goes beyond prompt engineering. You'll architect orchestration systems, memory layers, evaluation frameworks, and agent pipelines from the ground up.Working closely with company leadership, you'll have significant influence on product strategy, technical architecture, and future hiring decisions.
What You'll Own
Design and build multi-agent orchestration systems that detect, route, delegate, and resolve complex workflows autonomously
Implement episodic and semantic memory architectures, including vector databases, retrieval pipelines, and continuous learning mechanisms
Build action libraries and third-party integrations across enterprise applications, identity systems, SaaS platforms, and knowledge repositories
Develop LLM evaluation frameworks including prompt versioning, regression testing, and model benchmarking
Architect human-in-the-loop workflows with structured outputs, validation layers, retry logic, and graceful escalation paths
Instrument agent performance metrics, tracing, latency monitoring, and resolution analytics
Collaborate on knowledge graph, memory, and learning-loop architecture as the platform evolves
Required Qualifications
3+ years building production AI/ML systems serving real users and real traffic
Hands-on experience designing multi-step LLM applications with tool use, structured outputs, and workflow orchestration
Strong understanding of RAG architectures, chunking strategies, embeddings, hybrid retrieval, and re-ranking techniques
Proficiency in Java, Python, asynchronous programming patterns, REST APIs, and schema validation frameworks
Experience with evaluation-driven development and testing methodologies for AI systems
Ability to thrive in a fast-paced startup environment with high ownership and ambiguity
Nice to Have
Experience with IT service management, enterprise SaaS platforms, or operational workflow automation
Familiarity with AI governance, guardrails, and agent oversight frameworks
Experience building agent memory systems or long-horizon autonomous task execution
Knowledge of LLM observability and tracing tools
Familiarity with open-source foundation models and model selection strategies
Location: Bellevue, WA (Seattle area preferred)Compensation: $150,000-$300,000 DOE + equityTeam Size: 6
About the Company
Our client is a well-funded, early-stage startup building an AI-first enterprise automation platform where intelligent agents resolve operational tasks autonomously, learn from outcomes, and continuously improve over time.This is an opportunity to join as an early Applied AI Engineer and own a significant portion of the agentic AI stack from day one. You'll help shape both the technical direction and engineering culture while working alongside a highly experienced founding team.
The Role
You'll design and build the core AI agent framework powering an autonomous enterprise execution platform. This role goes beyond prompt engineering. You'll architect orchestration systems, memory layers, evaluation frameworks, and agent pipelines from the ground up.Working closely with company leadership, you'll have significant influence on product strategy, technical architecture, and future hiring decisions.
What You'll Own
Design and build multi-agent orchestration systems that detect, route, delegate, and resolve complex workflows autonomously
Implement episodic and semantic memory architectures, including vector databases, retrieval pipelines, and continuous learning mechanisms
Build action libraries and third-party integrations across enterprise applications, identity systems, SaaS platforms, and knowledge repositories
Develop LLM evaluation frameworks including prompt versioning, regression testing, and model benchmarking
Architect human-in-the-loop workflows with structured outputs, validation layers, retry logic, and graceful escalation paths
Instrument agent performance metrics, tracing, latency monitoring, and resolution analytics
Collaborate on knowledge graph, memory, and learning-loop architecture as the platform evolves
Required Qualifications
3+ years building production AI/ML systems serving real users and real traffic
Hands-on experience designing multi-step LLM applications with tool use, structured outputs, and workflow orchestration
Strong understanding of RAG architectures, chunking strategies, embeddings, hybrid retrieval, and re-ranking techniques
Proficiency in Java, Python, asynchronous programming patterns, REST APIs, and schema validation frameworks
Experience with evaluation-driven development and testing methodologies for AI systems
Ability to thrive in a fast-paced startup environment with high ownership and ambiguity
Nice to Have
Experience with IT service management, enterprise SaaS platforms, or operational workflow automation
Familiarity with AI governance, guardrails, and agent oversight frameworks
Experience building agent memory systems or long-horizon autonomous task execution
Knowledge of LLM observability and tracing tools
Familiarity with open-source foundation models and model selection strategies
Applied AI Engineer in bellevue at Unknown Company
This position is listed as full time and hybrid.