Staff Engineer / AI Builder - Mountain View

Robots and Pencils•Mountain View, CA

About The Position

Robots & Pencils is seeking a Staff AI Builder to lead the design and delivery of AI/ML systems. The role suits an experienced engineer who can make architectural decisions, own systems end-to-end, and provide technical leadership across a cross-functional team. The position involves defining AI architecture, leading model development and optimization, solving integration challenges, establishing engineering standards, and helping shape how the company’s AI systems scale. The work is production-focused, with reliability, security, and scalability as key concerns. The engineer will design and build agentic workflows and RAG pipelines; integrate AWS Bedrock and Agent Core; develop production prompts, evaluation, observability, and failure-handling systems; and build backend services and serverless architectures using Python, Node.js, and AWS. The role also includes event-driven orchestration, frontend integration, deployment, monitoring, and production troubleshooting. The engineer will collaborate with product, design, and delivery leads, mentor engineers, and own assigned features and releases through debugging and hardening. Robots & Pencils states that it ships production-ready AI in 30 to 45 days.

Requirements

At least 6 years of professional software engineering experience, including meaningful experience shipping GenAI/LLM-powered systems in production.
Hands-on depth in agentic AI, including reasoning loops, tool or function calling, and multi-agent orchestration, with judgment about when single-agent design is preferable.
Practical RAG expertise, including chunking strategies, embeddings, vector databases such as OpenSearch or similar, cosine similarity search, and re-ranking.
Experience building evaluation and observability for LLM systems, including golden datasets, LLM-as-judge, RAGAS or comparable metrics, and tracing tools such as LangFuse or LangSmith.
Strong prompt engineering skills, including the ability to write structured production system prompts with meaningful constraints.
Hands-on experience with the AWS GenAI stack, including Bedrock, Agent Core, Lambda, DynamoDB single-table design, S3, SQS, EventBridge, and Step Functions.
Strong Python and Node.js skills, with experience building full-stack applications and RESTful APIs.
Understanding of production reliability patterns for LLM-backed systems, including retries and backoff, circuit breakers, and fallback models.
Experience with containerization using Docker and cloud-native deployment.
Ability to own ambiguous, integration-heavy problems and explain technical decisions in depth.

Nice To Haves

Direct experience with Amazon Bedrock Agent Core, including agent registration, MCP tool wiring, memory and session management, and gateway provisioning.
Experience in a regulated or high-stakes domain such as education, healthcare, or financial services.
Familiarity with workflow orchestration tools such as Step Functions, Sequencer, or similar state-machine-based systems.
A point of view on LLM observability tools based on experience running them in production.

Responsibilities

Design and build agentic workflows using reasoning loops, tool or function calling, and single- or multi-agent orchestration.
Build and maintain RAG pipelines, including chunking, embeddings, vector search, re-ranking, and refreshing dynamic knowledge sources.
Integrate AWS Bedrock and Agent Core, including designing MCP-based tools with precise descriptions.
Write and iterate on production system prompts using structured role framing, output constraints, and few-shot examples.
Build evaluation and observability into agents using golden datasets, RAGAS-style metrics, LLM-as-judge, and tracing tools such as LangFuse or LangSmith.
Design for LLM failures with retries, backoff and jitter, circuit breakers, fallback models, and clear user-facing degradation behavior.
Build backend services in Python and Node.js, including serverless architectures using AWS Lambda and API Gateway.
Design DynamoDB single-table schemas for conversation state, agent memory, and session history.
Support event-driven orchestration with Step Functions, SQS, and EventBridge, emphasizing reliability and error handling.
Contribute to frontend integration so agentic features work well for end users, and write clean, well-tested code across the stack.
Support deployment, monitoring, and production troubleshooting in cloud-native environments using AWS and Docker.
Bring informed technical judgment to architecture discussions and articulate trade-offs among design patterns.
Partner with product, design, and delivery leads across global teams to scope and ship features end-to-end.
Mentor engineers and improve agentic engineering practices, including use of AI-assisted development tools such as Claude Code.
Own assigned features and releases end-to-end, including debugging, hardening, and maintaining production trustworthiness.