Senior AI Engineer

tenvyro-tech; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

Ulvior is seeking a senior software engineer to design and deploy production-grade AI applications using Python, FastAPI, and modern AI frameworks. You will build LLM-powered solutions with OpenAI, Claude, Gemini, and open-source models, and develop RAG pipelines with LangChain and vector databases.

Join a team shaping AI-enabled backend systems, architect AI agents and automated workflows, and optimize inference performance across cloud deployments.

Qualifications

• 5+ years of professional software engineering experience with hands-on AI/ML development.
• Proficiency in Python, FastAPI, REST APIs, and backend architecture.
• Experience building AI apps with LLMs and Generative AI.
• Experience with RAG, LangChain, and vector databases.
• Ability to design AI agents and multi-agent workflows with tool integration.
• Understanding embeddings, prompt engineering, evaluation, and inference optimization.
• Experience with PostgreSQL, Redis, and vector search technologies.
• Familiarity with PyTorch, Hugging Face, TensorFlow, or scikit-learn.
• Experience deploying apps using cloud infrastructure and containerization.
• Strong software architecture, performance optimization, testing, and production reliability.
• Excellent problem-solving and communication of technical decisions.

Responsibilities

• Design, develop and deploy production-ready AI applications using Python, FastAPI and modern AI frameworks.
• Build LLM-powered applications using OpenAI, Claude, Gemini, and open-source models.
• Develop and optimize RAG pipelines using LangChain, LangGraph, embeddings and vector databases.
• Architect AI agents, multi-agent systems and automated workflows with reliable tool integration.
• Integrate AI capability with backend APIs, PostgreSQL, Redis, and enterprise systems.
• Implement model evaluation, prompt optimization, fine-tuning, and inference performance improvements.

Skills

Problem-solving

Communication

Tools

Python

FastAPI

REST APIs

LLMs

LangChain

RAG

Vector databases

PostgreSQL

Redis

pgvector

Pinecone

FAISS

PyTorch

Hugging Face

TensorFlow

scikit-learn

OpenAI

Claude

Gemini

Cloud infra

Containerization

Job description

Qualifications

• 5+ years of professional software engineering experience, including hands-on AI/ML development.
• Strong proficiency in Python, FastAPI, REST APIs, and backend architecture.
• Practical experience developing applciations with LLMs and Generative AI.
• Hands-on experience with RAG, LangChain, and vector databases.
• Experience building AI agents using function calling, tool integration, and workflow orchestration.
• Understanding of embeddings, prompt engineering, model evaluation, and inference optimization.
• Experience with PostgreSQL, Redis, and vector search technologies such as pgvector, Pinecone, or FAISS.
• Familiarity with PyTorch, Hugging Face, TensorFlow, or scikit-learn.
• Experience deploying applications using cloud infrastructure and containerization.
• Strong understanding of software farchitecture, performance optimization, testing, and production reliability.
• Excellent problem-solving skills and ability to communicate technical decisions effectively.

Responsibilities

• Design, develop and deploy production-ready AI applications using Python, FastAPI and modern AI frameworks.
• Build LLM-powered applications using OpenAI, Claude, Gemini, and open-source models.
• Develop and optimize RAG pipe lines using Langchain, LangGraph, embeddings and vector databases.
• Architect AI agents, multi-agent systems and automated workflows with reliable tool integraions.
• Integrate AI Capability with backend APIs, PostgreSQL, Redis, and enterprise systems.Imple
• Implement model evaluation, prompt optimization, fine-tuning, and inference performance inprovements.