AI Applied Engineer — Backend & GenAI Systems

About the role We are building advanced

AI-driven backend systems

that power real-time conversational agents, character-based story engines, and multi-language TTS experiences. We are looking for an

AI Engineer

to join our team who can work directly with our lead developer to scale and evolve our GenAI platform.

If you have strong backend engineering skills and hands‑on experience deploying LLMs using

vLLM multi-GPU , this role is for you.

What you'll be doing

Build, maintain, and optimize

FastAPI microservices

Integrate and scale

vLLM multi-GPU inference

for high-throughput LLM serving

Design and maintain

FAISS-based RAG pipelines

Implement real-time TTS streaming, including F5TTS socket communication

Develop branching story engines, emotion/motion tagging, and character logic

Build robust loaders for HR documents, knowledge bases, and embeddings

Manage MongoDB collections and vector store metadata

Support compliance-friendly AI agent workflows (rule-based + hybrid AI)

Tech Stack You’ll Use

Python , FastAPI

vLLM

(multi-GPU, tensor parallelism)

FAISS , LangChain

MongoDB

Socket programming

(TCP/WebSockets)

Kafka / Redis Streams / similar streaming tech

TTS engines : F5TTS (with motion + facial-expression control)

Docker , basic CI/CD

Job Requirements Must Have

2–4+ years of experience as an AI Engineer or Backend Engineer

Experience running LLMs in production using vLLM (preferably multi-GPU)

Experience with FAISS or other vector databases

Experience building APIs with FastAPI

Understanding of embeddings, RAG, and memory buffers

Experience with async I/O and concurrent systems

Create workflow diagrams and charts to demonstrate the functionality of programs before coding them.

Work with team members to find creative, innovative solutions to problems.

English communication skills, both conversational and written.

Nice to Have

Knowledge of GGUF / quantization

Experience with real-time TTS

Familiarity with story/game engines or narrative logic

Basic frontend skills (React)

Experience working with streaming architectures

Experience with unit testing for RAG/vector stores

Portfolio/GitHub Please attach your portfolio/GitHub and examples of work involving:

vLLM or custom LLM inference

Vector search or TTS pipelines (optional)

Additional Questions

How many years' experience do you have as an Artificial Intelligence Developer?

#J-18808-Ljbffr