LLM Infrastructure Engineer
6 days ago
Houston, TX, United States
AMSYS Talent
Full-time
Free with email or Google
Save this job and keep your search organized
Create a free account to save jobs, create alerts and return to this listing from your dashboard.
Free with email or Google
By continuing, you agree to our Terms & Privacy Policy.
We are looking for a Senior Python / AI API Engineer to build and deploy production-grade services powering Large Language Model (LLM) applications. This role focuses on developing high-performance APIs for model inference, optimizing GPU workloads, and deploying AI services in cloud environments.
This is an engineering-focused role, not research. We are looking for someone who has built and shipped AI systems into production and understands the challenges of scalable inference and model serving.
Key Responsibilities
Develop high-performance APIs using Python (3.10+) and FastAPI Build and deploy LLM inference services using HuggingFace Transformers and PyTorch Optimize GPU workloads and CUDA memory usage Implement streaming inference APIs for real-time model responses Containerize and deploy services using Docker and GPU-enabled infrastructure Deploy AI workloads in Azure environments (AKS, ACI, or Container Apps) Required Skills
Strong Python development experience (3.10+) Hands-on experience building production APIs with FastAPI Experience with HuggingFace Transformers and PyTorch Solid understanding of REST API design Experience deploying containerized applications with Docker Nice to Have
Experience with OpenAI-compatible APIs, vLLM, or Text Generation Inference (TGI) Experience deploying AI workloads on Azure GPU infrastructure Familiarity with LoRA / PEFT fine-tuning Exposure to legal or financial NLP use cases
Ideal Candidate:
A hands-on engineer who understands how LLM systems run in production-from model loading and tokenization to GPU deployment and scalable APIs.
This is an engineering-focused role, not research. We are looking for someone who has built and shipped AI systems into production and understands the challenges of scalable inference and model serving.
Key Responsibilities
Develop high-performance APIs using Python (3.10+) and FastAPI Build and deploy LLM inference services using HuggingFace Transformers and PyTorch Optimize GPU workloads and CUDA memory usage Implement streaming inference APIs for real-time model responses Containerize and deploy services using Docker and GPU-enabled infrastructure Deploy AI workloads in Azure environments (AKS, ACI, or Container Apps) Required Skills
Strong Python development experience (3.10+) Hands-on experience building production APIs with FastAPI Experience with HuggingFace Transformers and PyTorch Solid understanding of REST API design Experience deploying containerized applications with Docker Nice to Have
Experience with OpenAI-compatible APIs, vLLM, or Text Generation Inference (TGI) Experience deploying AI workloads on Azure GPU infrastructure Familiarity with LoRA / PEFT fine-tuning Exposure to legal or financial NLP use cases
Ideal Candidate:
A hands-on engineer who understands how LLM systems run in production-from model loading and tokenization to GPU deployment and scalable APIs.