포지션 상세
bolttech is an international insurtech with a mission to build the world’s leading, technology-enabled ecosystem for protection and insurance. With a full suite of digital and data-driven capabilities, bolttech powers connections between insurers, distributors, and customers to make it easier and more efficient to buy and sell insurance and protection products.
A part of Pacific Century Group, bolttech serves customers in multiple markets across North America, Asia and Europe.
In this position you will…
...drive the development of custom Large Language Models (LLMs) across languages and modalities for bolttech AI-driven products. You will work on LLMs, prompt engineering, system integration, agents orchestration and more using frameworks such as Langchain, AWS Bedrock, or similar. This role offers an opportunity to innovate in an insurtech environment, delivering next generation Gen AI solutions that modernize how the business operates, working closely with the Head of AI, data scientists, engineers, and product manager.
・Designing and deploying custom solutions on AWS Bedrock by using foundation models from leading providers.
・Creating and managing Chatbots and conversational workflows using tools such as Langgraph or similar.
・Fine-tuning and evaluating large language models through Mosaic AI Gateway or designated computing resources and automated evaluation framework by using proprietary and external datasets.
・Building scalable APIs and backend services to support real-time AI inference including but not limited to GenAI or Agentic AI based AI solution.
・Architecting multi-stage agentic workflows and optimized RAG systems using the Mosaic AI Agent Framework and Vector Search.
・Ensuring reliability, privacy, and accuracy of Gen AI responses by applying testing and monitoring tools.
・Contributing to governance efforts by ensuring generative AI solutions follow responsible AI principles, including transparency, data privacy, and compliance with industry standards.
・Working with the data science team to apply generative AI to other business areas, including document processing, claims decisioning, and reporting.
・Documenting solutions and collaborating with engineering, product, and customer teams to align requirements and output.
・Tracking industry trends and recommending tools or approaches to improve system performance and capability.
・Experience with AWS Bedrock or similar.
・Experience with LLM Agentic workflows and framework (Langchain, LangGraph, LlamaIndex etc.)
・Knowledgeable in designing and implementing multi-layered AI safety architectures and adversarial red teaming strategies, utilizing frameworks such as Guardrails AI, or DeepTeam.
・Advanced knowledge of Python and some experience in ML frameworks (PyTorch, JAX etc.) for training, fine-tuning, and deploying generative models is preferred.
・Solid grasp of NLP techniques, multimodal AI (text, image, code), and agent workflows.
・Knowledge and experience with transformer architectures, prompt engineering, retrieval-augmented generation (RAG), and LLM evaluation methodologies.
・Knowledge of designing, implementing and managing distributed training pipelines for LLMs to ensure scalability and efficiency are nice to have.
・Knowledge of Mosaic AI (Gateway, Training, Serving), MLflow (Tracing/Evaluate), Vector Search and Databricks Asset Bundles (DABs) are also nice to have.
・Ability to contribute both independently and as part of a team.
・Excellent analytical and problem-solving skills.
・Excellent listening, communication, interpersonal and presentation skills to articulate complex technical ideas to cross-disciplinary internal and external stakeholders.
A part of Pacific Century Group, bolttech serves customers in multiple markets across North America, Asia and Europe.
In this position you will…
...drive the development of custom Large Language Models (LLMs) across languages and modalities for bolttech AI-driven products. You will work on LLMs, prompt engineering, system integration, agents orchestration and more using frameworks such as Langchain, AWS Bedrock, or similar. This role offers an opportunity to innovate in an insurtech environment, delivering next generation Gen AI solutions that modernize how the business operates, working closely with the Head of AI, data scientists, engineers, and product manager.
주요업무
・Building and integrating generative AI applications for customer interactions by using LLMs and orchestration frameworks.・Designing and deploying custom solutions on AWS Bedrock by using foundation models from leading providers.
・Creating and managing Chatbots and conversational workflows using tools such as Langgraph or similar.
・Fine-tuning and evaluating large language models through Mosaic AI Gateway or designated computing resources and automated evaluation framework by using proprietary and external datasets.
・Building scalable APIs and backend services to support real-time AI inference including but not limited to GenAI or Agentic AI based AI solution.
・Architecting multi-stage agentic workflows and optimized RAG systems using the Mosaic AI Agent Framework and Vector Search.
・Ensuring reliability, privacy, and accuracy of Gen AI responses by applying testing and monitoring tools.
・Contributing to governance efforts by ensuring generative AI solutions follow responsible AI principles, including transparency, data privacy, and compliance with industry standards.
・Working with the data science team to apply generative AI to other business areas, including document processing, claims decisioning, and reporting.
・Documenting solutions and collaborating with engineering, product, and customer teams to align requirements and output.
・Tracking industry trends and recommending tools or approaches to improve system performance and capability.
자격요건
・5+ years of experience in machine learning engineering, generative AI and LLM technologies, and Agentic workflows, or equivalent experience.・Experience with AWS Bedrock or similar.
・Experience with LLM Agentic workflows and framework (Langchain, LangGraph, LlamaIndex etc.)
・Knowledgeable in designing and implementing multi-layered AI safety architectures and adversarial red teaming strategies, utilizing frameworks such as Guardrails AI, or DeepTeam.
・Advanced knowledge of Python and some experience in ML frameworks (PyTorch, JAX etc.) for training, fine-tuning, and deploying generative models is preferred.
・Solid grasp of NLP techniques, multimodal AI (text, image, code), and agent workflows.
・Knowledge and experience with transformer architectures, prompt engineering, retrieval-augmented generation (RAG), and LLM evaluation methodologies.
・Knowledge of designing, implementing and managing distributed training pipelines for LLMs to ensure scalability and efficiency are nice to have.
・Knowledge of Mosaic AI (Gateway, Training, Serving), MLflow (Tracing/Evaluate), Vector Search and Databricks Asset Bundles (DABs) are also nice to have.
・Ability to contribute both independently and as part of a team.
・Excellent analytical and problem-solving skills.
・Excellent listening, communication, interpersonal and presentation skills to articulate complex technical ideas to cross-disciplinary internal and external stakeholders.
