AI Engineer — Production LLM & Agentic Workflows

Wwshemi; San Francisco (CA); On-site; USD 150,000 - 180,000; Full time

Job summary

Wwshemi in San Francisco is seeking a software engineer to build agentic AI systems that automate complex workflows across regulated domains. You will ship production LLM services with a focus on reliability, safety, and useful outcomes for customers.

You will own production RAG pipelines, vector databases, embeddings, and indexing, and implement multi-agent orchestration, tool-calling, memory, and reasoning features.

Qualifications

• 2-8 years of software engineering experience delivering shipped user-facing or backend products, including substantive AI engineering experience.
• Production experience deploying LLM-based services, including prompt design, orchestration, and tool integration.
• Full-stack proficiency with Python and TypeScript/React, plus cloud experience such as AWS or GCP and databases.
• Working knowledge of RAG, vector databases, embeddings, and retrieval pipelines.
• Experience building automated tests, evaluations, and monitoring for production AI systems.
• Experience designing API-driven, high-throughput systems and real-time features.
• Experience with agent or workflow frameworks and orchestration tools; familiarity with fine-tuning or multimodal models.

Responsibilities

• Build and maintain agentic systems for multi-step workflows across healthcare, legal, fintech, logistics, and compliance.
• Own production RAG pipelines and retrieval infrastructure, including vector databases, embeddings, and indexing.
• Implement multi-agent orchestration, tool-calling, memory, and reasoning features.
• Build evaluation and safety infrastructure to track model performance and identify regressions.
• Develop full-stack AI products, including APIs, data models, frontend and backend features, and production operations.
• Use CI/CD, testing, monitoring, user feedback, and telemetry to improve deployed systems.
• Work with product and design partners to prioritize work and define success measures.

Skills

Python

TypeScript/React

AWS

GCP

Databases (SQL/NoSQL)

RAG

Vector databases

Embeddings

Retrieval pipelines

API design

Testing & monitoring

Agent/workflow frameworks

Orchestration tools

Tools

CI/CD pipelines

Job description

Wwshemi in San Francisco is seeking a software engineer to build agentic AI systems that automate complex workflows across regulated domains. You will ship production LLM services with a focus on reliability, safety, and useful outcomes for customers.

You will own production RAG pipelines, vector databases, embeddings, and indexing, and implement multi-agent orchestration, tool-calling, memory, and reasoning features.