Artificial Intelligence Engineer

For one of our banking clients we are looking for an Prompt Engineer within our Data Integration and Monitoring team, you will play a critical role in the transformation and modernization of log management systems. Your focus will be on onboarding, transforming, and optimizing both structured and unstructured data for observability platforms such as Splunk, Microsoft Sentinel, and emerging technologies like Cribl.

You will work in close collaboration with security and application monitoring engineers to ensure seamless log ingestion, high-fidelity parsing, and end-to-end data quality for enterprise-wide monitoring use cases. A major part of this role involves contributing to a strategic migration from legacy ingestion pipelines (e.g., ArcSight connectors, Logstash) to a unified Cribl-based solution.

In parallel, you will leverage your expertise in Large Language Models (LLMs) to develop scalable and cost-efficient prompt engineering strategies that enhance log parsing capabilities, automation, and monitoring fidelity across the stack.

Key Responsibilities

• Prompt Engineering for Log Parsing:
• Design and fine-tune prompt strategies to interpret diverse log formats (e.g., syslog, JSON, proprietary app logs) using LLMs. Apply few-shot learning and prompt variant testing to support automated parser generation and validation.
• Monitoring & Quality Assurance:
• Develop LLM-driven health checks for log source availability, parsing accuracy, ETL workflows, and schema validation. Utilize AI-derived metrics such as token confidence and match rate to enhance parsing reliability.
• Model Adaptation & Optimization:
• Apply advanced model adaptation techniques including QLoRA and reinforcement learning to handle edge-case scenarios in log ingestion. Continuously monitor and optimize prompt performance (latency, confidence, token usage) for production scalability.

Required Qualifications

• Minimum 2 years of hands-on experience in prompt engineering and LLM-based automation.
• Strong understanding of LLM fine-tuning approaches, particularly using QLoRA and RLHF (Reinforcement Learning with Human Feedback).
• Demonstrated ability to build effective few-shot learning prompts and conduct structured A/B prompt testing.
• Proficient in evaluating model responses using statistical and probabilistic confidence metrics.
• Experience with Retrieval-Augmented Generation (RAG) and Contextual RAG (CRAG) frameworks.
• Familiarity with monitoring and optimizing token usage, latency, and cost-efficiency in LLM applications.
• Proficiency in JavaScript, with practical experience using Azure OpenAI Service for model deployment and tuning.

Preferred Attributes

• Background in data integration, log pipeline architecture, or observability engineering.
• Experience working on cross-functional teams involving security operations, DevOps, or control room monitoring.
• Strong collaborative mindset and ability to mentor or upskill team members in AI-driven workflows.

This role sits at the intersection of AI, observability, and cybersecurity—with room to shape a new standard for intelligent monitoring.

For inquiries you can reach out to [email protected]