Role Overview
We are seeking an AI Engineer who can lead design, development, and deployment of LLM-driven & AI-powered solutions. The ideal candidate will be comfortable working with tools such as Lovable, Tercel (or equivalent deployment environments), Claude (Anthropic) or similar LLMs, and will take ownership from ideation through production.
Key Responsibilities
- Develop, fine-tune and deploy large language model (LLM) based applications (e.g., conversational agents, summarisation, question-answering) using Claude and similar platforms.
- Evaluate and integrate tools such as Lovable/AIGeneration tools and Tercel (or comparable) frameworks for prompt engineering, model deployment, and scalable inference.
- Build pipelines to ingest and clean broker/insurance data, feed into AI models, and deliver insights via Ennabl's platform.
- Collaborate with product, data science, engineering & UX teams to embed AI capabilities within the Ennabl platform.
- Monitor model performance, drift, latency and ensure robustness, reliability and scalability in production.
- Implement best practices in MLOps: version control of models, CI/CD for AI, monitoring & logging of model usage and performance.
- Stay abreast of AI/LLM advancements, bring innovation to the team, recommend new architectures or tools.
- Provide documentation, code reviews and mentoring of junior engineers when applicable.
Required Qualifications & Skills
- Bachelor's or Master's degree in Computer Science, Engineering, Data Science or equivalent experience.
- 3 + years of hands-on experience working with LLMs (Claude, GPT family, etc.), prompt engineering and production deployment.
- Experience with tools/platforms like Lovable (or equivalent AI generation tool) and Tercel (or similar serverless/edge deployment frameworks).
- Strong programming skills in Python; experience with AI libraries (Transformers, HuggingFace, etc.).
- Solid understanding of MLOps: containerisation (Docker), model serving, CI/CD pipelines, monitoring (Prometheus, Grafana) and cloud deployment (AWS, GCP or Azure).
- Familiarity with data engineering: data ingestion, cleaning, feature engineering for AI workflows.
- Excellent problem-solving skills, ability to translate business requirements into AI solutions.
- Good communication and collaboration skills; ability to work across product & engineering teams.
Preferred Skills
- Previous experience in insurance/insur-tech domain or working with broker/hub data.
- Hands-on deployment of multilingual LLMs, retrieval-augmented generation (RAG) pipelines and vector stores (Pinecone, FAISS).
- Experience with tools like LangChain, LlamaIndex or similar frameworks for LLM orchestration.
- Edge or serverless deployment experience (Vercel, Netlify or similar).
- Understanding of model compliance, bias/fairness considerations, data privacy/regulation in insurance context.
