Live opening · Posted 18 days ago
At a glance
The key details from the original listing.
Your early-applicant advantage
Live timing from JobBeeper.
About the role
Description supplied by the original job listing.
Responsibilities:
Bedrock Integration: Replace the currentclaude.aideep -link (cosmetic "Ask AI" button) with a real Amazon Bedrock (Claude) integration for both Canopy and Trellis.
Context Injection: Build context-aware prompts that pull in real portfolio data, rather than the current no-context implementation.
Prompt Engineering: Design and maintain AI prompt templates (per-app, built twice) and expand the prompt library during Phase 2 feature refinement.
Model Selection and Inference-Cost Management: Implement configuration-driven model selection routing routine work to smaller/cheaper models and complex analysis to frontier models as the primary cost lever for Bedrock spend.
Audit Logging: Enable and route prompt/response audit logging to centralised logging and satisfy the audit-trail requirement.
Collaborate with product managers, data scientists, and software engineers to identify AI/ML opportunities and develop innovative solutions.
Implement and deploy AI/ML algorithms and models into production environments.
Optimise and fine-tune AI/ML models to improve accuracy and efficiency.
Conduct experiments, perform data analysis, and present findings to stakeholders.
Develop and maintain documentation for AI/ML algorithms, models, and solutions.
Stay up-to-date with the latest AI/ML research and technologies and apply them to improve our platform.
Mentor and provide technical guidance to junior AI/ML engineers or team members.
Requirements:
Bachelor's or Master's degree in Computer Science, Engineering, Mathematics, or related fields.
Ideally 6+ years of experience in building AI models with ML, NLP and deep learning.
Strong interest in AI and strong desire to do AI research.
Should have strong experience in Prompt Engineering.
Python and Python ecosystem for AI/ML development.
Familiarity with LLM concepts, information retrieval, recommendation engines and predictive AI.
Data engineering skills.
Ability to help write scripts to move data, clean data, and shape data for usage with LLMs.
Familiarity with tooling and APIs using inference engines hosted elsewhere, e. g., on openai.com .
Good understanding of AWS services.
Experience
7-11 yrs
More openings worth a look
Recently tracked roles with full details and direct application links.