AI Engineer

About the Role

We are looking for an AI Engineer to design, build, and maintain production-grade AI systems across our product and data platforms. You will work at the intersection of large language models, agentic workflows, and scalable MLOps infrastructure, owning end-to-end delivery from data ingestion through to model deployment and monitoring.

In addition, this role includes hands-on responsibility for internal IT infrastructure and end-user computing in a growing team environment.

What You'll Do

AI Engineering & Systems Development

· Design and develop LLM-powered applications including RAG pipelines, prompt engineering systems, and fine-tuned model integrations for production use cases

· Build and maintain multi-agent AI systems using orchestration frameworks (e.g. LangGraph, or equivalent), including tool use, memory management, and agent-to-agent communication

· Construct robust data pipelines for feature engineering, ingestion, transformation, and serving — ensuring data quality and lineage across the ML lifecycle

· Implement and manage MLOps infrastructure including model registries, CI/CD for ML, experiment tracking, and automated retraining workflows

· Deploy and monitor models in cloud environments, establishing observability tooling for latency, drift, and reliability

· Evaluate and integrate third-party AI services, vector databases, and embedding models into production stacks

· Document architectures, conduct code reviews, and contribute to internal engineering best practices

In-house IT & Infrastructure Support

· Manage and maintain internal office IT infrastructure, including network setup, routers, switches, and connectivity troubleshooting

· Implement and monitor data backup strategies (local and cloud) to ensure data integrity, security, and disaster recovery readiness

· Configure and provision user workstations, including OS setup, software installation, access control, and security policies

· Provide technical support to employees on hardware, software, and network-related issues

· Maintain IT documentation, asset inventory, and standard operating procedures for internal systems

· Ensure basic cybersecurity hygiene, including user access management, endpoint protection, patching, and updates

Required Skills

· 2–5 years of hands-on software or ML engineering experience

· Proficiency in Python; familiarity with TypeScript is a plus

· Experience with LLM APIs (Open AI, Anthropic, Gemini) and prompt engineering techniques

· Practical knowledge of RAG architectures and vector databases (e.g. Pinecone, Weaviate, pgvector)

· Exposure to agentic frameworks such as LangChain, LangGraph, or CrewAI

· Solid understanding of ML fundamentals: training, evaluation, fine-tuning, and model drift

· Experience with MLOps tooling: MLflow, Weights & Biases, or equivalent

· Cloud platform experience — AWS, GCP, or Azure (containerisation with Docker/Kubernetes preferred)

· Basic knowledge of IT infrastructure, networking, and end-user system support

Good to Have

· Familiarity with LLM evaluation frameworks (RAGAS, DeepEval, or customevals)

· Knowledge of guardrails, safety filtering, and responsible AI practices

· Experience working in an agile / squad-based delivery model

· Exposure to IT security best practices and backup/recovery systems

Why Krislite (https://www.krislite.com)

Join Krislite, a top player in the lighting industry, and be part of a dynamic, forward-looking team that values initiative, collaboration, and growth. Work alongside experienced colleagues across design, procurement, logistics, and site operations to deliver impactful lighting solutions for our clients.

As a company embracing automation and AI-driven tools, we continuously enhance our processes to work smarter and create better outcomes for our clients and our team. We welcome energetic individuals with a proactive and progressive mindset who are eager to contribute, learn, and grow together with the company.