Senior Staff Engineer - AI Infra & Semantic Search

Wwshemi; San Francisco (CA); Hybrid; USD 150,000 - 215,000; Full time

Job summary

Wwshemi in San Francisco is seeking a senior backend engineer to build production-grade, secure distributed systems powering AI-driven evidence search and analysis. You will deploy LLMs and ML components, design RAG pipelines, and architect semantic data layers to support investigative workflows.

The role requires 6+ years in backend engineering with leadership, a strong security mindset, and experience across startups and established tech firms. Hybrid work in SF is offered.

Qualifications

• 6+ years building distributed backend systems and leading initiatives.
• Hands-on experience deploying LLMs or other ML systems to production.
• Proficiency in Python; familiarity with JavaScript/React is a plus.

Responsibilities

• Build resilient, secure distributed systems for AI-powered evidence search.
• Deploy large language models, vision models, and ML systems in production.
• Design retrieval-augmented generation pipelines for unstructured data.
• Architect data systems with query planning and semantic modeling.
• Develop or integrate agentic systems for investigative data analysis.
• Stay current with evolving AI models and infrastructure approaches.

Skills

Distributed systems

Backend leadership

Python

JavaScript/React

RAG pipelines

Semantic modeling

Security & resilience

Startup experience

Tools

LLM deployment tooling

Semantic search infra

Job description

Wwshemi in San Francisco is seeking a senior backend engineer to build production-grade, secure distributed systems powering AI-driven evidence search and analysis. You will deploy LLMs and ML components, design RAG pipelines, and architect semantic data layers to support investigative workflows.

The role requires 6+ years in backend engineering with leadership, a strong security mindset, and experience across startups and established tech firms. Hybrid work in SF is offered.