Offer summary

Qualifications:

2+ years of experience in AI/ML or full-stack software engineering., Proficient in Python and/or Node.js with experience in building LLM-based applications., Solid experience with MongoDB, including vector search capabilities., Strong communication skills to explain AI concepts to non-technical stakeholders..

Key responsibilities:

Design and implement AI-driven applications and conversational agents using LLMs.

Build and maintain RAG pipelines and develop prompting strategies.

Collaborate with cross-functional teams to bring prototypes into production.

Manage CI/CD pipelines and ensure code quality with proper testing and documentation.

Job description

Halo believes in innovation by inclusion to solve digital problems. As an international agency of over 200 people specializing in interactive media strategy and development, we embrace equity and empowerment in a serious way. Our interdisciplinary teams of unique designers, developers and entrepreneurial minds with a variety of backgrounds, viewpoints, and skills connect to solve business challenges of every shape and size. We empathize to form deep, meaningful relationships with our clients so they can do the same with their audience. Working at Halo feels like belonging. Learn more about our philosophy, benefits, and team at https://halopowered.com/As an AI Architect, you will lead the design of scalable, secure, and modern technology solutions, leveraging artificial intelligence, cloud platforms, and microservices—while ensuring alignment with AI governance principles, agile delivery, and platform modernization strategies

Overview

We’re seeking AI Engineers to help design, build, and deploy next-gen AI solutions across Mercer’s global ecosystem. You will work on Generative AI, RAG pipelines, and AI agents that power internal tools, chatbots, and decision-support systems used by our consultants. This hands-on engineering role bridges full-stack software development and advanced AI techniques.

Requirements

Design and implement AI-driven applications, copilots, and conversational agents using LLMs (OpenAI, Anthropic, Azure OpenAI).
Build and maintain RAG pipelines using text chunking, embeddings, and vector databases (e.g., MongoDB Atlas Vector Search, FAISS, Pinecone, Weaviate).
Develop and optimize prompting strategies and agent reasoning logic.
Engineer LLM-based middleware integrations using Python and Node.js.
Contribute to full-stack application development using the MEAN stack (MongoDB, Express, Angular, Node.js).
Support secure architecture by implementing MFA, OAuth flows, and containerized deployments.
Manage CI/CD pipelines using GitHub and Jenkins, and work with containerized deployments.
Collaborate with cross-functional teams (data scientists, product owners, platform engineers) to bring prototypes into production.
Maintain code quality, observability, and robustness with proper testing and documentation.

Required Skills & Qualification

2+ years of experience in AI/ML or full-stack software engineering.
Hands-on experience building LLM-based applications, RAG solutions, or AI agents.
Proficient in Python and/or Node.js and familiar with modern backend/middleware patterns.
Solid experience in MongoDB, including vector search capabilities (Atlas Vector Search preferred).
Experience with MEAN stack (MongoDB, Express, Angular, Node.js).
Familiarity with prompt engineering, embeddings, and retrieval pipelines.
Experience implementing or integrating Multi-Factor Authentication.
Comfortable using GitHub for source control and Jenkins for CI/CD automation.
Excellent problem-solving skills and the ability to communicate technical concepts.
Strong communication skills – able to explain AI concepts to non-technical stakeholders.

Good to have

Experience with Databricks, model registries, and MLOps workflows.
Familiarity with LangChain, LlamaIndex, Dapr, or Azure AI Agent Service.
Prior work in AI observability, testing, and platform governance.
Understanding of cloud security, data governance, and compliance in AI systems.