Staff AI Architect

Robots and Pencils

1d•$146,071 - $201,541

About The Position

At Robots & Pencils, we design AI systems for a human world. Our name says it all. Robots and pencils means engineering paired with creativity, because every agent we ship has to work for real people in real workflows. That balance is baked into how we operate. Every role here contributes directly to that mission. Here, you shape how AI systems integrate into enterprise operations, how teams move at real velocity, and how products create measurable impact for clients and the people they serve. We ship production-ready AI in 30 to 45 days. That pace demands people who take ownership, lead with craft, and care deeply about what they put their name on.

Requirements

7+ years of professional software engineering experience, with at least 3 years in AI/ML architecture or technical leadership roles
Deep expertise in LLM and agentic application architecture, including multi-agent orchestration and tool-calling patterns
Strong experience designing production RAG and retrieval systems, including hybrid retrieval, reranking, and vector store selection
Strong experience with model serving and inference optimization on AWS, including latency, throughput, and cost tuning
Deep understanding of LLMOps and MLOps, including eval pipelines, prompt versioning, CI/CD, and observability for AI workloads
Demonstrated experience with AI evaluation, guardrails, and tracing tooling
Strong judgment on fine-tuning versus prompting versus RAG tradeoffs for accuracy, cost, and maintainability
Expert software engineering background, with proficiency in Python and at least one other language (e.g., TypeScript, Java, Go)
Strong background in cloud-native architecture, including microservices, serverless, containerization, and event-driven systems
Strong understanding of responsible AI and governance, including data isolation, prompt-injection defense, and compliance
Demonstrated leadership and technical mentoring experience across a team
Demonstrable, day-to-day usage and expert knowledge of AI-forward tools such as Claude and Cursor
Excellent problem-solving skills and the ability to navigate highly ambiguous technical and business challenges with sound judgment

Nice To Haves

AWS AI certifications, fine-tuning or model customization experience, or responsible AI experience is a plus

Responsibilities

Define AI system architecture and lead design across LLM applications, agentic systems, retrieval, and ML model serving for end-to-end engagements
Drive RAG and context-engineering strategy, including hybrid retrieval, reranking, chunking, and embedding model selection across vector stores
Lead multi-agent orchestration design using frameworks such as LangGraph, Amazon Bedrock Agents, or AgentCore
Own model serving and inference architecture on AWS, optimizing latency, throughput, and cost with streaming, caching, batching, and quantization
Define LLMOps and MLOps standards across engagements, including prompt versioning, eval pipelines, CI/CD, and feature stores
Drive evaluation, guardrails, and observability strategy, establishing offline and online eval, LLM-as-judge scoring, and tracing
Own the responsible AI posture for AI systems, including governance, PII and data isolation, prompt-injection defense, and grounding controls that reduce hallucination
Lead decisions on build approach, including fine-tuning, prompting, RAG, and tool use, weighing accuracy, cost, and maintainability
Bring an AI-forward mindset to your daily work, using tools like Claude, Cursor, and other modern AI assistants to ship higher-quality work at pace
Partner with leadership and clients on AI technical direction, translating business goals into architectural decisions
Communicate complex AI concepts and tradeoffs clearly to engineering and non-engineering stakeholders alike
Engage closely with engineering, data, ML, and product teams to align AI architecture with broader business priorities
Develop and maintain AI architecture documentation, evaluation standards, and reusable patterns
Establish architectural standards and best practices that lift quality and consistency across the team
Mentor junior and mid-level engineers, helping them grow their architectural thinking and craft
Act as a technical escalation point on complex architectural and integration challenges
Evaluate emerging technologies and recommend tools, frameworks, and patterns that improve architecture over time