Lead Software Engineer – GenAI / GCP

Valiant Technologies LLC; Minneapolis (MN); On-site; USD 77,000 - 110,000; Full time

Job summary

Valiant Technologies LLC seeks a Lead Software Engineer focused on GenAI and GCP to build enterprise-grade AI solutions. You will design, develop, and deploy LLM-based apps, implement RAG workflows, and optimize performance across cloud platforms.

The role requires hands-on Python expertise, experience with Vertex AI and DocAI, and strong NLP/DL fundamentals. Candidates should be familiar with embeddings, vector databases, and REST services for scalable production deployments.

Qualifications

• Hands-on experience with Python and ML frameworks.
• Experience with Vertex AI and Document AI (DocAI).
• Strong NLP, ML, and DL fundamentals; PyTorch preferred.
• Experience with OpenAI APIs and open-source LLMs.
• Familiarity with embedding models, vector databases, and semantic search.

Responsibilities

• Design, develop, and implement enterprise-grade Generative AI solutions.
• Build RAG-based applications using retrieval, embeddings and vectors.
• Develop Agentic AI workflows using LangGraph, CrewAI or similar frameworks.
• Fine-tune, deploy and optimize LLMs for performance and scalability.
• Create intelligent document processing solutions with OCR and DocAI.
• Work with Python, FastAPI/Flask to build robust REST services.
• Leverage cloud platforms (GCP/AWS/Azure) for production-grade deployments.
• Ensure scalable, reliable AI applications for enterprise use cases.

Skills

Python

Vertex AI

Document AI

NLP

ML

Deep Learning

PyTorch

LLMs

Embedding models

Vector databases

FastAPI

Flask

REST APIs

Docker

GCP

AWS

Azure

LangGraph

CrewAI

Tools

Google Vertex AI

Google Document AI

LangGraph

CrewAI

Docker

REST APIs

FastAPI

Flask

Job description

US Citizen, Green Card, H-1B, OPT-EAD, CPT, Other

Job Title: Lead Software Engineer - GenAI/GCP
Location: Minneapolis, MN
Duration: 6 Months + Extension
Bill Rate: $68/hour
Job Type: W-2, 1099, C2C
Client: To Be Discussed Later
Work Authorization: US-Citizen, H-1B, OPT-EAD, GC-EAD

Job Description

Strong hands-on experience in Python, Google Vertex AI, and Google Document AI (DocAI).

Design, develop, and implement enterprise-grade Generative AI and LLM-based solutions.

Build RAG-based applications using retrieval, embeddings, and vector databases.

Implement enterprise-level Agentic AI workflows using LangGraph, Google ADK, CrewAI, or similar frameworks.

Experience with LLM fine-tuning, deployment, optimization, and performance tuning.

Develop intelligent document processing solutions using OCR, Google Document AI, and automated data extraction.

Strong understanding of NLP, Machine Learning, Deep Learning, and PyTorch.

Experience working with OpenAI APIs and open-source Large Language Models (LLMs).

Hands-on experience with vector databases, embedding models, and semantic search.

Develop scalable AI applications using Python, FastAPI, Flask, and REST APIs.

Experience with Docker and containerized application deployment.

Strong cloud experience with GCP, AWS, or Azure.

Build and integrate AI-powered applications for enterprise business use cases.

Optimize AI solutions for scalability, reliability, performance, and production deployment

We are an equal opportunity employer. All aspects of employment including the decision to hire, promote, discipline, or discharge, will be based on merit, competence, performance, and business needs. We do not discriminate on the basis of race, color, religion, marital status, age, national origin, ancestry, physical or mental disability, medical condition, pregnancy, genetic information, gender, sexual orientation, gender identity or expression, national origin, citizenship/ immigration status, veteran status, or any other status protected under federal, state, or local law.