Full Stack Engineer

We are seeking a Python AI Backend Developer to join our software engineering team and help design, develop, and support modern AI-powered applications. This individual will follow the software development lifecycle to analyze requirements, create technical designs, develop scalable backend systems, and implement Retrieval-Augmented Generation (RAG) solutions using leading LLM technologies.

The ideal candidate will have experience building Python-based APIs, integrating large language models, developing vector database solutions, and collaborating with cross-functional teams to deliver high-quality software.

Responsibilities

Design, develop, test, debug, and document software applications following established SDLC processes.

Review functional requirements and translate them into technical designs and implementation plans.

Develop scalable backend services and APIs using Python.

Build and maintain Retrieval-Augmented Generation (RAG) pipelines for AI-powered applications.

Implement document ingestion workflows, embedding strategies, and retrieval architectures.

Design and optimize vector database solutions for semantic search and knowledge retrieval.

Integrate large language models (LLMs) through OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, and similar platforms.

Participate in architecture reviews, design discussions, and code reviews.

Develop and maintain system documentation, operational procedures, and technical specifications.

Collaborate with engineering, product, and data teams to ensure quality, consistency, and performance.

Implement automated testing, monitoring, logging, and observability best practices.

1-5 years of Python development experience building backend applications and APIs.

Experience with FastAPI, Flask, or Django and developing REST-based services.

Hands-on experience designing and implementing RAG (Retrieval-Augmented Generation) pipelines.

Experience with LLM frameworks and APIs such as LangChain, LlamaIndex, OpenAI, Anthropic, Azure OpenAI, or AWS Bedrock.

Experience working with at least one vector database (Pinecone, Weaviate, Qdrant, Milvus, ChromaDB, or pgvector).

Experience with cloud and deployment technologies including Docker, CI/CD, and AWS/Azure/GCP environments., 1-5 years of Python development experience building backend applications and APIs.

• Experience with FastAPI, Flask, or Django and developing REST-based services.

• Hands-on experience designing and implementing RAG (Retrieval-Augmented Generation) pipelines.

• Experience with LLM frameworks and APIs such as LangChain, LlamaIndex, OpenAI, Anthropic, Azure OpenAI, or AWS Bedrock.

• Experience working with at least one vector database (Pinecone, Weaviate, Qdrant, Milvus, ChromaDB, or pgvector) GraphQL experience.

Experience with cloud and deployment technologies including Docker, CI/CD, and AWS/Azure/GCP environments.

Async programming (asyncio/aiohttp).

PostgreSQL, MongoDB, or Redis.

Kubernetes exposure.

Monitoring/observability tools such as OpenTelemetry or LangSmith.

This is onsite 4 days onsite in Greenwood Village Colorado offering 41-42/hr.