Large Language Model (LLM) Engineer

Job Description

About the role:

As a Prompt Engineer and LLM Specialist at Ignition, you'll play a critical role in leveraging Large Language Models (LLMs) to drive solutions that matter to customers. You'll collaborate closely with Product Managers, Engineers, and Data Scientists to optimize and refine prompt designs, evaluate models, and ensure our AI-driven initiatives deliver meaningful outcomes efficiently.

Reporting to the Head of Data and Analytics, your work will balance technical expertise with practical business acumen, empowering stakeholders to understand when and how to best utilize LLMs and related technologies. You'll foster an environment of continuous learning, experimentation, and pragmatism in adopting AI solutions.

What your day to day will look like:

• Collaborate with cross-functional teams, including Product Managers and Engineers, to identify opportunities where LLMs provide significant value compared to traditional methods.
• Iterate, test, and refine prompts for Large Language Models, focusing on maximizing accuracy, relevance, and efficiency.
• Assess various LLM providers and models, balancing factors such as accuracy, cost-effectiveness, latency, and ease of integration.
• Implement advanced AI techniques such as function calling and agent orchestration (e.g., coordinating multiple agents to complete tasks like data enrichment or summarisation).
• Apply retrieval and response enhancements such as hybrid retrieval, query rewriting, reranking, and guardrails to improve accuracy and control.
• Utilize low-code tools (e.g., N8N, Zapier) to integrate and automate LLM workflows efficiently across the business.
• Prototype and deliver internal LLM-powered tools (e.g., knowledge assistants, automated code snippets, ticket routing agents) to boost efficiency across support, ops, and engineering workflows.
• Contribute to the stability and cost-efficiency of LLM pipelines by implementing caching, monitoring, and performance optimization strategies.
• Provide guidance and best practices on AI ethics, transparency, and model governance, proactively addressing risks related to bias, compliance, and security.
• Communicate insights, progress, and technical decisions clearly to both technical and non-technical stakeholders, ensuring alignment and understanding across the business.

Qualifications

What you need to succeed:

• Demonstrated experience in designing, iterating, and refining prompts for LLMs, with a clear understanding of different prompting strategies.
• Strong analytical and critical thinking skills, capable of translating complex AI techniques into practical business applications.
• Experience evaluating LLM providers and balancing trade-offs around accuracy, latency, and cost.

Nice-to-have:

• Familiarity with cloud infrastructure (AWS, Azure, GCP) and containerization (Docker, Kubernetes).
• Experience with data science workflows and experimentation frameworks.
• Understanding or experience with business intelligence tools (Looker, Tableau, Power BI).
• What You’ve Done Before (or could show us):
• Built or contributed to an AI-powered product feature, internal tool, or automation using LLMs.
• Worked with data, product, or design stakeholders to define and deliver usable AI functionality.
• Explored the trade-offs between embeddings, LLMs, and traditional ML techniques.
• Created prototypes using OpenAI, Anthropic, or OSS models—and turned one into a stable internal or customer-facing capability.
• Have intermediate scripting skills (Python preferred) to debug LLM outputs and write automation scripts as needed.
• Familiarity with low-code automation tools (N8N, Zapier) to streamline and operationalize LLM workflows.
• Hands-on experience with vector databases and retrieval-augmented generation (RAG) methods.
• Familiarity with advanced AI techniques including agent orchestration, function calling, query rewriting, reranking, and implementing guardrails for model governance.
• Demonstrated ability to ship and maintain production-grade AI features, with attention to reliability, latency, and scalability.
• Excellent communication skills, capable of clearly presenting complex technical concepts to non-technical stakeholders.
• SQL proficiency preferred, valuable for inspecting data, understanding analytics pipelines, and contributing to prompt tuning tasks.
• Experience integrating and deploying LLMs at scale via platforms like AWS Bedrock or Snowflake is desirable.

Additional Information

Why join us:

Join our global SaaS scale-up company where we foster a collaborative, open, and transparent culture and work without ego. Our team comprises curious and intelligent colleagues who embrace challenges. Here's what we offer:

• Employee stock options from day one
• 20 days of accrued annual leave/vacation plus 10 wellbeing days to prioritize yourself and your loved ones
• Additional paid day off to celebrate your birthday, along with volunteering leave
• Health, dental, and vision benefits starting immediately
• Annual education allowance reimbursement to support your professional development
• Employee recognition program
• Quarterly wellness allowance to invest in your personal wellness
• Paid subscriptions to Headspace and LifeWorks EAP & Wellbeing Platform
• Flexible working arrangements, supported by WFH reimbursement and technology allowance to ensure your safety while working from home
• Personal tax return assistance (since we're in the accounting business!)
• Paid parental leave

Please consider applying, even if you don’t tick all the boxes. Research has shown that candidates from underrepresented minority groups often only apply for roles where they meet all the detailed criteria.  Experience comes in many forms, and skills are transferable. We are committed to adding diverse perspectives to our teams and encourage everyone to apply if interested.

Ignition is an equal opportunity employer and all qualified applicants will receive consideration for employment without regard to race, colour, religion, sex, sexual orientation, gender identity, national origin, disability, protected veteran status, or any other characteristic protected by law.

Ignition is proud to provide employment and recruitment accommodations during the recruitment process. Once our team reviews your resume and contacts you if there is a fit, we will work with you to meet your accessibility needs. For any questions, suggestions or required documents regarding accessibility in a different format, please contact [email protected]