4 hours ago
San Francisco, CA, USAMid Level / Senior
Base Salary
$150k - $180k/yr
Responsibilities
- Design and maintain agentic systems for multi-step workflows across regulated and enterprise domains.
- Build production retrieval-augmented generation pipelines and retrieval infrastructure using vector databases, embeddings, and indexing.
- Implement multi-agent orchestration, tool calling, memory, and reasoning components.
- Develop evaluation and safety tools to measure model performance, detect regressions, and support reliable production use.
- Deliver full-stack AI features spanning APIs, data models, frontend and backend implementation, testing, deployment, and monitoring.
- Partner with product and design teams to set priorities and success metrics and improve features using user feedback and telemetry.
Requirements
- Two to eight years of software engineering experience delivering user-facing or backend products, including production engineering in a product-focused environment.
- Practical experience deploying LLM services in production, including prompt design, orchestration, and tool integration.
- Proficiency with Python and TypeScript/React or equivalent, plus cloud platforms such as AWS or GCP and relational or NoSQL databases.
- Working knowledge of RAG, vector databases, embeddings, and retrieval pipelines.
- Experience building automated tests, evaluations, and monitoring for production AI systems, API-driven high-throughput systems, and real-time features.
- Familiarity with LangGraph, CrewAI, Temporal, or Trigger.
- Experience with multi-tenant or enterprise systems or regulated domains such as healthcare, fintech, or legal.
- Familiarity with fine-tuning or multimodal models is useful.
- A completed university degree and a track record of owning features from data model through deployment and monitoring.
Benefits
- On-site role in San Francisco, California.
- Visa sponsorship is not available.