AI LLM Engineer
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Role details
Tech stack
Job description
We are seeking a Senior AI LLM Engineer to design, deploy, and optimize production-grade conversational AI systems. You will build scalable tool-calling frameworks, integrate AI models with enterprise applications, and implement strict hallucination mitigation controls. A key focus of this role is developing traceable response systems and reusable explanation templates for complex financial calculations. Key Responsibilities AI Architecture & Production Deployment Deploy Solutions: Build and maintain scalable, production-grade LLM applications. Integrate Systems: Connect AI models with enterprise applications and secure APIs. Build Frameworks: Develop robust tool-calling frameworks to orchestrate model-API interactions. Prompt Engineering & Conversation Design Design Strategies: Create advanced prompt strategies and conversation management frameworks. Tune Responses: Optimize conversational context to ensure highly accurate user experiences. Mitigate Risks: Implement automated controls to detect and eliminate model hallucinations. Financial Logic & Traceability Ensure Traceability: Build mechanisms that provide auditable, step-by-step reasoning for generated outputs. Develop Templates: Create reusable explanation templates for pricing methods, revenue sharing models, and expense calculations. Optimize Performance: Conduct continuous prompt tuning and model optimization for cost, latency, and accuracy.
Requirements
Software Engineering: 5+ years of professional software development experience. LLM Expertise: 3+ years of hands-on experience working directly with Large Language Models. Prompt & Conversation Design: 3+ years of experience designing prompt strategies and managing conversation frameworks. Response Tuning: 3+ years of experience implementing, tuning, and auditing conversational AI outputs. o Providing traceable response generation. o Developing reusable explanation templates for pricing methods, revenue sharing models, and expense calculations. o Conducting prompt tuning and model optimization. o Implement hallucination mitigation controls. Technical Skills Proven track record of deploying production-ready AI solutions at scale. Deep understanding of API integration, tool-calling (function calling), and agentic workflows. Experience embedding regulatory compliance, financial traceability, or audit trails into AI responses.
Apply for this position
This job is hosted externally. Click below to view the full posting and apply.
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Good distractions
Talks and stories from around this role — technically off-topic, practically not.
Moments
Explore playlistsVideos
See allRelated articles
See all
How to Become an AI Engineer
MLOps And AI Driven Development
The Prompt Engineer ✍️
Who Owns Your Content in the Age of LLMs?