Swivel Group

headquartered in Australia is best known for building and implementing custom solutions for businesses to enable them to innovate, scale and compete at a global standard. We've been around since 2019, with a team growing beyond 160+ employees that help us challenge and innovate for our partners across the software, digital, and finance landscapes.

Our Brands : Swivel Tech, Swivel Finance, Swivel Foundation, HumaniseAI.

Role Overview

We are seeking a Senior AI Solutions Engineer to design, build, and deploy enterprise-grade Generative AI solutions for our clients. You will architect and implement complex AI agent systems, RAG pipelines, and LLM-powered applications that solve real business problems across industries including construction, healthcare, government, and professional services.

This role requires deep expertise in agentic AI architectures, prompt engineering, and cloud-native AI services. You will work on solutions involving multi-agent orchestration, document intelligence, semantic search, and cross-session memory systems.

Key Responsibilities

AI Architecture & Development

• Design and implement agentic AI systems using LangGraph, LangChain, or similar orchestration frameworks

• Architect multi-module AI solutions with complex state management, routing logic, and gating mechanisms

• Build production-grade RAG (Retrieval-Augmented Generation) pipelines with vector databases and semantic search

• Develop and optimise prompts for multi-turn conversations, structured outputs, and domain-specific tasks

• Implement cross-session memory systems for contextual awareness across user interactions

• Integrate LLM APIs (Claude, GPT, etc.) with appropriate error handling, retry logic, and cost optimisation

Document Processing & Intelligence

• Build document ingestion pipelines for PDF, DOCX, and structured data extraction

• Implement intelligent chunking strategies that preserve document structure and context

• Design and deploy semantic search solutions using Azure AI Search or similar vector stores

• Create document analysis workflows for compliance, summarisation, and information extraction

Cloud & Infrastructure

• Deploy AI solutions on Azure (preferred) or AWS using container services, serverless functions, and managed AI services

• Implement secure, scalable architectures with appropriate data sovereignty and compliance controls

• Design cost-effective infrastructure with auto-scaling and usage-based resource management

• Set up monitoring, logging, and observability for AI workloads (token usage, latency, error rates)

Full-Stack Integration

• Build RESTful APIs and WebSocket services for real-time AI interactions

• Collaborate with frontend engineers to create intuitive chat interfaces and AI-powered UX

• Implement streaming responses, typing indicators, and progressive content delivery

• Write clean, well-documented code following best practices and security standards

Leadership & Collaboration

• Lead technical design sessions and architecture reviews for AI projects

• Mentor junior engineers in AI/ML concepts, prompt engineering, and best practices

• Collaborate with solution architects and clients to translate business requirements into technical solutions

• Stay current with rapidly evolving AI landscape and evaluate new tools, models, and techniques

• Participate in Agile ceremonies including sprint planning, standups, and retrospectives

Experience Requirements

4-6 years of professional software engineering experience, with 1-2 years focused on Generative AI, LLM applications, or AI/ML solutions.

Required Technical Skills

Core AI/LLM Skills (Must Have)

• Strong experience with LangChain and/or LangGraph for agent orchestration

• Hands-on experience integrating LLM APIs (Claude/Anthropic, OpenAI, Azure OpenAI)

• Proven track record building production RAG systems with vector databases

• Advanced prompt engineering skills including system prompts, few-shot learning, and chain-of-thought

• Experience with embedding models and semantic similarity search

• Understanding of LLM limitations, hallucination mitigation, and grounding techniques

Cloud & Infrastructure (Must Have)

• Strong experience with Azure (preferred) or AWS cloud services

• Hands-on with Azure AI services: AI Search, Document Intelligence, Cosmos DB, Container Apps

• Experience with containerisation (Docker) and orchestration (Kubernetes or managed services)

• Knowledge of Infrastructure as Code

• Understanding of cloud security, networking, and compliance requirements

Programming & Development (Must Have)

• Proficiency in Python for AI/ML development and backend services

• Experience with TypeScript/JavaScript and modern frameworks (React, Next.js)

• Strong API design skills (REST, WebSocket, GraphQL)

• Proficiency with Git, CI/CD pipelines, and DevOps practices

• Experience with relational and NoSQL databases (PostgreSQL, Cosmos DB, MongoDB)

Nice to Have Skills

• Experience with Semantic Kernel (Microsoft) for enterprise AI orchestration

• Voice AI integration (VAPI, Azure Speech, or similar)

• Fine-tuning LLMs or working with open-source models (Llama, Mistral)

• Knowledge of AI agents frameworks beyond LangGraph (AutoGen)

• Experience with n8n, Make, or similar workflow automation platforms

• Background in NLP, information extraction, or document understanding

Required Attributes

• Ability to translate complex business requirements into technical AI solutions

• Strong problem-solving mindset with attention to edge cases and failure modes

• Excellent communication skills to explain AI concepts to non-technical stakeholders

• Self-motivated with ability to work independently and drive projects forward

• Collaborative team player who actively shares knowledge and mentors others

• Passion for staying current with rapidly evolving AI/LLM landscape

• Comfortable working with ambiguity in a fast-paced environment

Minimum Qualifications

Bachelor's degree in Computer Science, Software Engineering, Mathematics, or related technical field. Master's degree in AI/ML is a plus but not required with equivalent practical experience

Engagement

• Full -time, permanent

Work model

• Hybrid

Benefits

What We Can Offer You:

• A dynamic and supportive working environment
• Full medical benefits
• Training & Development
• Flexible and hybrid working arrangements
• Attractive remuneration

Work Culture

Swivel promotes a culture of positivity, openness, growth, collaboration, and fairness within our work environment. Individual development matters to us. We put in a sincere effort to help our team grow on professional and personal levels.

Swivel Values

Trust :

A confident relationship in our staff, that would adhere to transparency and honesty in our dealings

Innovation :

Initiative, collaboration, challenging the industry and continuously evolving

Premium:

Top talent, going above and beyond and treating your workplace as your own business

Respect:

Everyone matters and so do their ideas

Team:

Be supportive, welcoming, community, family-oriented and as strong as our weakest

Our Channels

Website - https://swiveltech.io

Instagram - https://www.instagram.com/swivel.group/

Facebook - https://www.facebook.com/swivelgroupau

LinkedIn - https://www.linkedin.com/company/swivelgroupau/