Senior Backend Engineer, AI Platform

TMTG • Sarasota, FL

2d • Remote

About The Position

The Senior Backend Engineer, AI Platform will help build AI-based features for a social media platform serving millions of users. Working directly with the platform architect and other developers, this person will contribute hands-on LLM-stack expertise and establish core AI infrastructure in a greenfield environment. The role also includes shaping engineering practices as the team grows.

The position involves building and operating production LLM-backed features and services, including retrieval-augmented generation, streaming responses, tool use, model-provider routing and failover, token streaming, usage metering, retrieval systems, and evaluation and instrumentation. The engineer will own services end to end, from schema design through deployment and on-call. The role is remote and limited to candidates based in the United States who are authorized to work in the United States.

Requirements

• At least 5 years of backend engineering experience in a statically typed language such as Go, Java, Kotlin, or C#.
• Experience shipping production LLM-backed features, including retrieval-augmented generation, streaming responses, and tool use, and supporting them after launch.
• Hands-on experience with LLM serving infrastructure, including multi-provider routing, failover, token streaming, and cost or usage metering.
• Experience building retrieval systems, including vector search, embedding pipelines, context assembly, and citation-backed answers.
• Ability to identify AI system failure modes and build instrumentation to detect them.
• Pragmatic experience evaluating AI answer quality, including relevance, safety, and source quality, through simple, repeatable tests.
• Strong API design skills and comfort owning a service end to end, from schema to deployment to on-call.
• Must be based in the United States and authorized to work in the United States.

Nice To Haves

• Go experience (strongly preferred).
• Python experience.
• Experience with LLM gateways or serving infrastructure such as LiteLLM, vLLM, or TGI.
• Experience with vector databases such as Qdrant or pgvector and embedding pipelines.
• Experience fine-tuning open-weight models, through LoRA or full fine-tunes, and with associated evaluation practices.
• Content moderation or safety tooling experience.
• Familiarity with Ruby on Rails or React/TypeScript.

Responsibilities

• Build AI-based features and core AI infrastructure for a platform serving millions of users.
• Develop and operate production LLM-backed features, including retrieval-augmented generation, streaming responses, and tool use.
• Build LLM serving capabilities such as routing across model providers, failover, token streaming, and cost and usage metering.
• Build retrieval systems, including vector search, embedding pipelines, context assembly, and citation-backed answers.
• Instrument systems to detect failure modes such as hallucinations, retrieval misses, provider outages, and cost overruns.
• Evaluate AI answer quality using repeatable tests for relevance, safety, and source quality.
• Own services end to end, from schema design through deployment and on-call.
• Help shape engineering practices as the team grows and integrate with Ruby on Rails and React/TypeScript systems.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed