Position: AI / Python Architect
Location: San Diego, CA / Dallas, TX / New Jersey (Hybrid)
Position type: Contract.
Client: Verizon
Position Overview
- We are seeking an experienced AI / Python Architect with strong expertise in scalable microservices, Python-based AI agent services, LLM orchestration, and event-driven architectures. The ideal candidate will have hands-on experience designing and deploying enterprise-grade AI solutions using Claude, Model Context Protocol (MCP), agent-based workflows, vector databases, and Apache Kafka.
- This role will be responsible for architecting scalable backend and AI services, developing intelligent agent workflows, and integrating LLM capabilities into enterprise applications.
Key Responsibilities
- Architect and deploy scalable microservices using Spring Boot and Spring Cloud.
- Design and develop robust RESTful and gRPC APIs to support enterprise applications and AI services.
- Design and develop Python-based AI agent services and AI-driven backend solutions.
- Develop and orchestrate LLM-powered applications using frameworks such as LangChain, LlamaIndex, AutoGen, and LangGraph.
- Design and implement LLM-powered solutions using Claude, including enterprise AI workflows and agent-based applications.
- Build and integrate Model Context Protocol (MCP) servers to enable AI agents to interact with tools, data, and enterprise systems.
- Create and implement AI agent skills and reusable agent capabilities.
- Design and develop AI-driven workflows for enterprise use cases.
- Work with vector databases to support LLM applications and intelligent retrieval capabilities.
- Apply advanced prompt engineering techniques to improve LLM performance and reliability.
- Architect and implement event-driven systems and real-time message streaming using Apache Kafka.
- Design Kafka-based solutions supporting scalable, reliable, and distributed enterprise applications.
- Collaborate with engineering and architecture teams to translate business requirements into scalable AI and backend solutions.
Required Technical Skills
AI / LLM
- Expert-level Python development experience.
- Strong hands-on experience with LLMs, specifically Claude.
- Strong experience with LLM orchestration frameworks such as:
- LangChain
- LlamaIndex
- AutoGen
- LangGraph
- Hands-on experience with AI agents and agentic workflows.
- Experience building MCP servers and working with the Model Context Protocol.
- Experience creating agent skills and AI-driven workflows.
- Strong prompt engineering experience.
- Deep knowledge of vector databases and their use in LLM applications.
Backend / Microservices
- Extensive experience architecting and deploying scalable microservices.
- Strong experience with Spring Boot and Spring Cloud.
- Strong experience designing and developing RESTful APIs and gRPC services.
- Experience developing Python-based AI agent services.
Event-Driven Architecture
- Deep expertise in Apache Kafka.
- Strong understanding of event-driven architecture and message streaming.
- Experience designing scalable Kafka-based distributed systems.
Ideal Candidate
The ideal candidate combines strong software architecture skills with deep hands-on AI/LLM engineering experience. This is not purely an AI research or prompt-engineering role. Candidates should be capable of building production-grade services, integrating LLMs and agents into enterprise systems, and designing scalable event-driven architectures.
Key areas of expertise:
Python | Claude | LLMs | AI Agents | MCP | LangChain | LangGraph | LlamaIndex | AutoGen | Vector Databases | Prompt Engineering | Spring Boot | Spring Cloud | REST | gRPC | Apache Kafka | Microservices