Senior Backend Engineer, AI Platform

TMTG

. Build AI-based features for a social media platform serving millions of users .

Posted 10/13/2026full-timeRemote • Florida • United StatesSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates extensive backend engineering expertise with a focus on AI-based features, LLM serving infrastructure, and strong API design. Proven ability to own services end to end, ensuring quality and safety in AI responses.

Highest-signal resume keywords

Backend Engineering ExperienceLLM Serving InfrastructureAPI Design SkillsProduction Experience with LLM-Backed FeaturesExperience with Vector Databases

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

GoJavaKotlinC#PythonLLM ServingRetrieval SystemsInstrumentation DesignContent ModerationFine-Tuning Models

Tools & Technologies

Ruby on RailsReactTypeScriptLiteLLMVLLMTGIQdrantPgvector

Industry Keywords

AI InfrastructureGreenfield EnvironmentSchema DesignDeploymentOn-Call Responsibilities

Tech Stack

Tools & technologies

AssemblyJavaKotlinPythonReactRubyRuby on RailsTypeScriptGo

About the role

Key responsibilities & impact

Build AI-based features for a social media platform serving millions of users
Work directly with the platform architect and other developers
Establish core AI infrastructure in a greenfield environment
Shape engineering practices as the team grows
Integrate services with Ruby on Rails and React/TypeScript
Own backend services end to end, from schema design through deployment and on-call
Build and operate LLM serving, retrieval, evaluation, instrumentation, and safety capabilities

Requirements

What you’ll need

5+ years of backend engineering experience in a statically typed language (Go, Java, Kotlin, C#)
Production experience shipping LLM-backed features, including retrieval-augmented generation, streaming responses, and tool use
Hands-on experience with LLM serving infrastructure, including routing across multiple model providers, failover, token streaming, and cost/usage metering
Experience building retrieval systems, including vector search, embedding pipelines, context assembly, and citation-backed answers
Ability to design instrumentation for hallucinations, retrieval misses, provider outages, and cost overruns
Experience measuring AI answer quality through relevance, safety, source quality, and repeatable evaluations
Strong API design skills
Ability to own a service end to end, from schema through deployment and on-call
US-based and authorized to work in the United States
Go strongly preferred
Python
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 using LoRA or full fine-tunes
Content moderation or safety tooling experience
Familiarity with Ruby on Rails or React/TypeScript