AI Large Language Mode (LLM) Junior Technology Architect

As a hands on AI Engineer, you will be at the heart of designing and building the components that make up advanced AI systems powering the modern enterprise. This is a deeply technical, hands-on engineering role - you will spend the majority of your time in the detailed design, development, integration, and testing of AI system components across classical machine learning, generative AI, and agentic systems, delivering these within active client engagements.

You will take detailed architecture and design specifications and translate them into working, production-quality software components. This means writing clean, well-structured code, making low-level design decisions within your assigned scope, and ensuring your components integrate reliably within the broader AI system. You will build and wire together the constituent parts of AI agent systems - including individual agent logic, tool integrations, skills, and memory components - and contribute to the development and integration of foundation and classical ML models into end-to-end pipelines.

A hands-on curiosity for the open source ecosystem is essential in this role. You will continuously evaluate, learn, and adopt relevant open source libraries and frameworks - such as those spanning agent orchestration, vector storage, model serving, and ML pipelines - selecting and applying the right ones for the problem at hand. Equally, you will configure, integrate, and operationalize third-party AI technologies and platform services, understanding their capabilities and constraints deeply enough to make them work reliably within the context of a larger enterprise system. You will engineer components with enterprise-grade qualities in mind, ensuring your work meets defined requirements across security, observability, governance, performance, and scalability. You will write and maintain the technical artifacts that accompany your engineering work - including low-level design documents, component specifications, and integration contracts - ensuring your work is well-documented, testable, and handoff-ready. You will operate as a practitioner within cross-functional delivery teams alongside data engineers, ML engineers, and application developers, taking direction from lead and principal architects while contributing meaningfully to technical problem-solving and design discussions within your domain. This role is an opportunity to build deep, hands-on expertise across the AI engineering stack, develop strong software engineering fundamentals applied to cutting-edge AI systems, and grow toward a lead engineer or architect role over time.

THE WORK

• Design, build, and configure individual agents - including their prompts, tools, and skills - and integrate them into multi-agent workflows

• Implement agent orchestration logic that handles task handoffs, communication, and error recovery

• Build evaluation harnesses and test suites that measure agent and component quality on metrics such as accuracy, relevance, and faithfulness, and share findings to inform design improvements

• Integrate foundation models into applications, selecting the appropriate model and invocation pattern for each use case

• Build and run model fine-tuning pipelines - including data preparation and training - to adapt models to specific business domains, applying working knowledge of transformer-based architectures

• Build ingestion pipelines that parse, chunk, enrich, and index unstructured enterprise content for retrieval

• Implement embedding generation, integrate vector databases, and develop retrieval components, including connectors and adapters that process unstructured content into end-to-end RAG pipelines

• Build the logic that assembles prompts and manages what information is passed to the model within its context window

• Implement memory components that store and recall conversational history and other relevant context

• Implement input/output guardrails, content filtering, and defenses against prompt injection

• Build PII detection and redaction components and integrate access controls for model and tool access

• Implement versioning, audit logging, and lineage tracking, and maintain model documentation that keeps the system auditable

• Instrument components with logging and tracing for requests, responses, token usage, and tool calls

• Contribute to monitoring, alerting, and cost tracking that keep AI systems healthy in production

• Continuously learn and apply new design patterns, technologies, and frameworks across the fast-evolving AI landscape, bringing fresh approaches to the components you build

• Collaborate within cross-functional teams to clarify requirements and ensure your components meet stakeholder needs

• Create and maintain clear technical documentation for the components you build, supporting troubleshooting and future development