Mid-Level AI Engineer

Clera is hiring a Mid-Level AI Engineer to build agentic systems and production LLM services for regulated and enterprise workflows. The role focuses on reliability, safety, and measurable customer outcomes, with ownership across key components of the AI stack and full-stack product delivery.

Role Overview

You will develop and maintain production-ready AI capabilities, including RAG pipelines, orchestration, evaluation and safety infrastructure, and end-to-end delivery of AI product features. Work spans multi-step agent workflows and enterprise integrations across multiple domains.

Responsibilities

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

Required Qualifications

• Two to eight years of software engineering experience shipping user-facing or backend products, with substantive AI engineering experience in a product-focused environment.
• Production experience deploying LLM-based services, including prompt design, orchestration, and tool integration.
• Full-stack proficiency with Python and TypeScript/React (or equivalent), plus cloud experience 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.
• Experience designing API-driven, high-throughput systems and real-time product features.
• Experience with agent or workflow frameworks and orchestration tools; familiarity with fine-tuning or multimodal models is also useful.
• Background in multi-tenant or enterprise systems, or regulated industries including healthcare, fintech, or legal.
• Ability to operate with end-to-end ownership, sound engineering judgment, and a collaborative, user-focused approach.

Technologies

• Python
• TypeScript, React
• AWS, GCP
• RAG, vector databases, embeddings
• CI/CD
• Relational databases, NoSQL databases

Compensation

• Base salary: USD 150,000 to 180,000 per year

Location

On-site in San Francisco, California, United States.

Visa Sponsorship

Visa sponsorship is not available.