GenAI Engineer

SGA Inc.
Irving, United States of America
5 days ago

Role details

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

Job location

Irving, United States of America

Tech stack

API
Artificial Intelligence
Amazon Web Services (AWS)
Azure
Continuous Integration
Python
Open Source Technology
Performance Tuning
TensorFlow
Software Construction
Software Engineering
Systems Integration
TypeScript
Web Applications
Google Cloud Platform
PyTorch
Large Language Models
Prompt Engineering
Generative AI
Backend
GIT
HuggingFace
Data Management
Virtual Agents
Docker
Microservices

Job description

  • AI Agent Development: Build and orchestrate AI agents using frameworks like LangChain, AutoGen, or CrewAI, implementing self-healing workflows (e.g., Act-Verify-Refine loops). LLM Integration & Backend: Develop robust backend systems using Python and TypeScript, integrating LLMs into microservices architectures. Data Management for LLMs: Utilize vector databases (Pinecone, Milvus, Weaviate) for agent memory and architect Retrieval-Augmented Generation (RAG) pipelines to enhance LLM accuracy and contextual understanding. Prompt Engineering: Design and optimize prompt strategies, including automated evaluation frameworks, for high-quality LLM output. Context Engineering: Manage LLM information ecosystems, including system prompts, RAG implementation, and conversation history. MLOps & Deployment: Oversee the end-to-end lifecycle of generative models, focusing on inference speed, cost-efficiency, and scalability on cloud platforms (AWS, Google Cloud Platform, Azure). AI Ethics & Compliance: Ensure adherence to security standards, IP regulations, and safety guidelines for all generative models. Tool Orchestration: Define and manage the API/tool access for AI agents to optimize accuracy.

Requirements

  • Technical Proficiency: Strong command of Python, PyTorch, TensorFlow, and Hugging Face libraries. GenAI Experience: Hands-on experience with LangChain, LlamaIndex, vector databases, and fine-tuning techniques (LoRA, QLoRA). API & Backend: Proven ability to integrate AI models into web applications via APIs (OpenAI, Anthropic). Software Engineering: Solid understanding of software engineering best practices, including Git, CI/CD, and Docker.

Preferred Skills:

  • Experience with multimodal AI models (image, video, audio generation). Published AI/LLM research or contributions to open-source AI projects. Background in AI governance or safety policy development.

About the company

SGA is a technology and resource solutions provider driven to stand out. We are a women-owned business. Our mission: to solve big IT problems with a more personal, boutique approach. Each year, we match consultants like you to more than 1,000 engagements. When we say let's work better together, we mean it. You'll join a diverse team built on these core values: customer service, employee development, and quality and integrity in everything we do. Be yourself, love what you do and find your passion at work. Please find us at .

Apply for this position