Staff Engineer / AI Builder - Mountain View

Description

The company designs AI systems for real-world use and ships production-ready AI in 30 to 45 days, so the team values ownership, craft and accountability for the work.

This is a staff-level role leading the design and delivery of AI and ML systems. You will set architecture direction, lead model development and optimization, and take on hard integration problems across a cross-functional team.

You will work on live projects where reliability, security and scalability matter. You will set engineering standards and influence technical decisions that determine how the company's AI work grows over time.

The ideal candidate enjoys making architectural calls and can own systems from start to finish while guiding the technical direction of the team.

Responsibilities

• Design and build agentic workflows with reasoning loops, tool and function calling, and orchestration across single-agent and multi-agent setups, choosing the pattern that fits each problem.
• Build and maintain RAG pipelines covering chunking, embeddings, OpenSearch vector search, re-ranking, and refresh logic for knowledge sources that change often.
• Connect systems to AWS Bedrock and Agent Core, including MCP-based tools with descriptions clear enough that the orchestrator always routes correctly.
• Write and refine production system prompts with defined roles, output limits and few-shot examples.
• Add evaluation and observability to every agent: golden datasets, RAGAS-style metrics, LLM-as-judge as a runtime guardrail and offline check, and tracing with LangFuse, LangSmith or similar.
• Plan for LLM failure: retries with backoff and jitter, circuit breakers, fallback models, and a clear user-facing message when an upstream dependency degrades.
• Build backend services in Python and Node.js, including serverless designs on AWS Lambda and API Gateway that support agent workflows.
• Design DynamoDB single-table schemas with composite keys and transactional writes for conversation state, agent memory and session history.
• Support asynchronous agent operations using Step Functions, SQS and EventBridge, with attention to reliability and error handling.
• Contribute to frontend integration so agent 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 on AWS and Docker, with senior engineers advising where needed.
• Weigh the real trade-offs in architecture discussions, such as gateway centralization against latency or single-agent against multi-agent design.
• Work with product, design and delivery leads across global teams to scope and ship features end to end.
• Mentor engineers on the pod and raise agentic engineering practices, including use of AI-assisted tools such as Claude Code.
• Own assigned features and releases end to end, including debugging, hardening and keeping production systems reliable.

Requirements

• 6+ years of professional software engineering experience, including real time spent shipping GenAI or LLM systems to production, not only prototypes.
• Hands-on depth in agentic AI: reasoning loops, tool and function calling, multi-agent orchestration, and a clear view of when single-agent design is better.
• Practical RAG experience with chunking strategies, embeddings, vector databases such as OpenSearch, cosine similarity search and re-ranking, and the ability to explain how each works.
• Experience building evaluation and observability for LLM systems, including golden datasets, LLM-as-judge, RAGAS or similar metrics, and tools like LangFuse or LangSmith.
• Strong prompt engineering skills, with the ability to write a structured production system prompt with constraints when asked.
• Hands-on work with the AWS GenAI stack: Bedrock, Agent Core, Lambda, DynamoDB with 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 reliability patterns for LLM-backed systems, including retries with backoff, circuit breakers and fallback models used together.
• Experience with Docker and cloud-native deployment.
• Comfort with ambiguous, integration-heavy problems and the ability to go deeper when challenged rather than staying abstract.

Conditions

The posted salary range is $165,604 to $228,491 USD. Final pay may fall above or below this range and the range may change over time.

Pay within the range depends on factors including education, qualifications, certifications, experience, skills, seniority, geographic location, performance, shift, travel requirements, sales or revenue metrics, collective bargaining agreements, and business needs.

The company is an equal opportunity employer.

Benefits

• Paid time off, medical, dental and vision insurance, and a 401(k) plan for eligible employees.