Full Stack Developer

InfoVision, Inc.
Irving, United States of America
1 month ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English
Experience level
Senior

Job location

Irving, United States of America

Tech stack

Java
Artificial Intelligence
Amazon Web Services (AWS)
Amazon Web Services (AWS)
Server Applications
Cloud Computing
Code Review
Distributed Systems
Python
Software Architecture
Smart Devices
Network Routers
System Availability
Large Language Models
Spring-boot
Servicebus
Event Driven Architecture
Containerization
Kubernetes
HuggingFace
TensorRT
Api Gateway
REST
Docker
Microservices

Job description

  • Design and develop robust server-side applications and RESTful microservices using Java (Spring Boot) and Python, ensuring scalability, security, and high availability across distributed systems.
  • Architect and deploy cloud-native solutions on AWS leveraging services including Lambda, ECS, API Gateway, SageMaker, S3, and EventBridge.
  • Fine-tune open-weight LLM models (e.g., LLaMA, Mistral, Phi) using frameworks such as Hugging Face PEFT and LoRA for domain-specific enterprise use cases.
  • Deploy and manage AI/LLM inference runtimes on edge devices including laptops, on-premise servers, and network routers using tools such as Ollama, llama.cpp, or TensorRT-LLM.
  • Build and maintain CI/CD pipelines for containerized microservices and edge AI model deployments using Docker, Kubernetes, and AWS DevOps tooling.
  • Conduct code reviews, contribute to architectural decisions, and mentor junior engineers on AI-integrated full stack development practices.

Requirements

  • 10+ years of full stack development experience with strong server-side proficiency in Java (Spring Boot) and Python.
  • Telecom Industry experience is a must.
  • Hands-on experience building and deploying microservices on AWS, including services such as Lambda, ECS, API Gateway, and SageMaker.
  • Demonstrated experience fine-tuning LLM models using Hugging Face Transformers, PEFT, or LoRA.
  • Proven ability to deploy and optimize LLM inference on edge devices (CPU/edge GPU) using runtimes such as Ollama, llama.cpp, or ExecuTorch.
  • Proficiency with containerization and orchestration tools including Docker and Kubernetes.
  • Strong understanding of RESTful API design, event-driven architectures, and distributed microservices patterns.

Apply for this position