Senior AI Engineer

This is a fully remote position, open to applicants in Florida.

📋 Description

• Develop AI-driven features for a social media platform with millions of active users.

• Oversee the AI engineering initiatives while collaborating closely with the platform architect and fellow developers.

• Establish core AI infrastructure within a greenfield setting.

• Influence engineering practices as the team expands.

• Design and manage services comprehensively, from schema design to deployment and on-call duties.

• Create LLM serving infrastructure that includes multi-provider routing, failover mechanisms, token streaming, and cost/usage monitoring.

• Develop retrieval systems featuring vector search, embedding pipelines, context assembly, and citation-supported answers.

• Implement systems to identify hallucinations, retrieval misses, provider outages, and cost overruns.

• Set up practical, repeatable evaluation methods for relevance, safety, and source quality.

• Integrate services with Ruby on Rails and React/TypeScript frameworks.

⛳️ Requirements

• At least 5 years of experience in backend engineering.

• Proficiency in a statically typed language such as Go, Java, Kotlin, or C#.

• Proven experience in delivering LLM-supported features, including retrieval-augmented generation, streaming responses, and tool utilization.

• Practical experience with LLM serving stacks, including aspects like multi-provider routing, failover, token streaming, and cost/usage monitoring.

• Skilled in building retrieval systems that employ vector search, embedding pipelines, context assembly, and citation-backed answers.

• Capability to design instrumentation for identifying hallucinations, retrieval misses, provider outages, and cost overruns.

• Familiarity with evaluating AI response relevance, safety, and source quality through straightforward, repeatable tests.

• Strong skills in API design and the ability to take ownership of a service from start to finish.

• Must reside in the U.S. and be authorized to work in the United States.

• Preference for candidates experienced with Go.

• Experience with Python is a plus.

• Familiarity with LLM gateways or serving infrastructures such as LiteLLM, vLLM, or TGI.

• Experience with vector databases like Qdrant or pgvector, as well as embedding pipelines.

• Background in fine-tuning open-weight models using LoRA or full fine-tuning techniques.

• Experience in content moderation or safety tooling is advantageous.

• Knowledge of Ruby on Rails or React/TypeScript is a plus.

🏝️ Benefits

• Equal opportunity employer.

• Censorship-free, accessible platform.

• Dynamic, rapidly growing company dedicated to promoting free speech.