Architect Software Developer

Quantiphi • Fredericton, NB

1d • Remote

About The Position

We are seeking an Architect Software Developer to design and build intelligent, scalable applications powered by large language models and agentic workflows. This role will focus on developing backend services and AI-driven systems using modern Python frameworks and LLM orchestration tools. The Architect Software Developer will be responsible for building and maintaining AI-powered services that support the Agentic platform. They will work closely with AI/ML engineers, product teams, and platform engineers to implement scalable backend services, integrate LLM orchestration frameworks, and enable seamless integration with enterprise systems. The ideal candidate has strong Python expertise, hands-on experience with LangChain and LangGraph, and a deep understanding of building production-grade AI applications. Experience with Java-based backend systems is considered a strong asset.

Requirements

• 10+ years of experience in Software Development, primarily focused on backend engineering.
• Strong expertise in Python and modern backend frameworks such as FastAPI or Flask.
• Hands-on experience with LLM orchestration frameworks such as LangChain and LangGraph.
• Experience building AI-powered applications, conversational systems, or agentic workflows.
• Strong understanding of microservices architecture, asynchronous programming, and distributed systems.
• Strong expertise in asynchronous programming patterns in Python (asyncio, aiohttp) for handling concurrent LLM API requests efficiently.
• Experience with API development and design, including RESTful services and OpenAPI/Swagger documentation.
• Proven experience building APIs that serve as integration points between different technology stacks (e.g., Python services communicating with Java/Spring Boot backends).
• Working knowledge of Java and Spring Boot, with the ability to understand and integrate with existing Java-based microservices architectures.
• Hands-on experience integrating with LLM provider APIs (OpenAI, Anthropic, Google Vertex AI, Azure OpenAI) including handling streaming responses, token management, and API rate limits.
• Familiarity with vector databases and retrieval systems used in AI pipelines.
• Experience with cloud platforms such as AWS, GCP, or Azure for deploying and scaling applications.
• Hands-on experience implementing CI/CD pipelines, containerization (Docker), and infrastructure automation.
• Strong debugging, performance optimization, and system troubleshooting skills.
• Experience working in Agile development environments with cross-functional teams.

Nice To Haves

• Experience implementing Retrieval-Augmented Generation (RAG) pipelines.
• Familiarity with vector databases such as Pinecone, Milvus, Weaviate, or PGVector.
• Exposure to prompt engineering, tool-calling frameworks, and structured LLM outputs.
• Understanding of agent orchestration patterns and multi-agent systems.
• Experience with MLOps platforms or model serving frameworks.
• Knowledge of streaming data pipelines, message queues (Kafka, RabbitMQ), or event-driven architectures.
• Exposure to enterprise system integrations and secure API design.
• Experience building production-grade AI applications with measurable business impact.

Responsibilities

• Design, develop, and maintain scalable backend services and APIs that serve as the integration layer between AI-powered services and the main React/Java Spring Boot application.
• Build and maintain RESTful APIs that send and receive data to/from LLM providers, implementing proper error handling, streaming responses, and rate limiting.
• Build intelligent agent orchestration pipelines using LangChain, LangGraph, and related LLM frameworks.
• Develop microservices and async backend systems optimized for high throughput, reliability, and performance.
• Design and build integration layers that enable smooth communication between Python microservices and the main React/Java Spring Boot application, ensuring data consistency and low latency.
• Develop microservices that seamlessly integrate with existing Java Spring Boot services through well-defined API contracts and communication protocols.
• Collaborate with frontend (React) and backend (Java) teams to ensure consistent data models and API specifications across the platform.
• Define and implement clear API specifications (using OpenAPI/Swagger) to facilitate seamless data exchange between Python-powered AI services and the enterprise Java Spring Boot backend.
• Implement efficient request handling patterns for LLM API calls, including proper error handling, retry logic, rate limiting, and response streaming where applicable.
• Develop robust API endpoints and service interfaces to enable seamless integration across internal and external systems.
• Implement asynchronous processing patterns to handle long-running LLM tasks without blocking frontend user experiences.
• Architect services capable of horizontal scaling to handle increased throughput when multiple requests hit the LLM APIs simultaneously.
• Continuously optimize system performance, scalability, and reliability across AI-powered services.
• Implement integrations between LLM-based services and enterprise systems such as identity providers, knowledge systems, databases, and observability platforms.
• Collaborate with AI/ML teams to integrate model-serving platforms and deploy production-grade AI workflows.
• Ensure strong code quality through unit testing, integration testing, and CI/CD best practices.
• Contribute to system design discussions and assist in producing technical documentation and architecture artifacts.
• Participate in code reviews, mentor junior engineers, and promote engineering best practices.

Benefits

• Work where innovation happens - work with disruptive innovators in a research-focused organization with 60+ patents filed across various disciplines.
• Stay ahead of the curve—immerse yourself in breakthrough AI, ML, data, and cloud technologies and gain exposure working with Fortune 500 companies.
• Ample opportunities to learn, grow and interact with colleagues from varied experience and backgrounds around the globe.
• Fun, diverse and hybrid work culture.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed