Applied AI Engineer

Mission US

3d•Remote

About The Position

The Applied AI Engineer will help design, implement, and scale Mission’s enterprise AI platform and intelligent automation capabilities. This hands-on, execution-focused role builds production-ready AI applications, agentic workflows, and integrations with large language models and machine learning services to enable AI-powered experiences across underwriting, operations, finance, HR, and other business functions. The engineer collaborates with technology and business teams to deliver secure, scalable, reusable AI solutions and establish best practices for AI engineering, governance, and operational excellence. The role includes developing cloud-native AI services, integrating AI with enterprise platforms and data sources, creating prompt engineering and knowledge retrieval solutions, evaluating and optimizing models and workflows, and implementing testing, monitoring, security, governance, and responsible AI controls. The engineer also supports production systems, builds reusable components and frameworks, and keeps current with emerging AI technologies and practices.

Requirements

At least 3 years of experience in software engineering, AI engineering, machine learning, or a related technical field, including at least 2 years designing and delivering production AI solutions.
Hands-on experience building enterprise applications using LLMs, AI memory and context management, AI agents, prompt engineering, and orchestration frameworks.
Experience deploying applied AI features and related cloud-native technologies.
Strong programming skills in Python or JavaScript, with experience developing RESTful APIs, microservices, and scalable distributed applications.
Experience integrating AI solutions with enterprise systems using REST APIs, event-driven architectures, vector databases, and knowledge repositories.
Familiarity with modern AI or orchestration frameworks.
Experience implementing AI evaluation, monitoring, observability, and testing frameworks to measure model quality, reliability, latency, and cost.
Understanding of responsible AI principles, security, governance, prompt safety, model access controls, and enterprise AI compliance.
Experience with Git, GitLab or GitHub, CI/CD pipelines, Infrastructure as Code, and DevOps/MLOps practices for deploying AI applications.
Experience working with Databricks, SQL Server, or other enterprise data platforms.
Experience with modern cloud environments such as AWS, Azure, or Google Cloud Platform.
Bachelor’s degree in Computer Science, Software Engineering, or equivalent practical experience.
Ability to translate complex business problems into scalable, secure, production-ready AI solutions and collaborate effectively with cross-functional teams.
Must live in the United States and be authorized to work in the United States without employment sponsorship or a visa.

Nice To Haves

Experience developing AI solutions for the property and casualty insurance industry, including underwriting, submissions, or policy administration.
Experience with Model Context Protocol (MCP), enterprise AI agents, multi-agent systems, vector databases, and modern AI engineering platforms.
Strong communication skills and ability to work cross-functionally with different departments.
Ability to travel up to 10% of the year.

Responsibilities

Design, develop, and deploy production-grade AI solutions using large language models, AI agents, memory and context management patterns, and machine learning techniques.
Build intelligent workflows and AI-powered applications to automate business processes across underwriting, operations, finance, and other enterprise functions.
Develop and maintain scalable AI services using modern cloud-native architectures.
Integrate AI capabilities with enterprise platforms, including policy administration, submission management, data platforms, document management, and external data providers.
Design and implement prompt engineering, orchestration frameworks, vector databases, and knowledge retrieval solutions.
Evaluate, fine-tune, and optimize foundation models and AI workflows for accuracy, latency, scalability, and cost efficiency.
Develop evaluation frameworks, automated testing, and monitoring to measure AI quality, hallucination rates, response accuracy, and system performance.
Implement AI guardrails, security controls, governance standards, and responsible AI practices.
Collaborate with product owners, business stakeholders, business analysts, and engineers to translate business requirements into scalable AI solutions.
Build AI solutions using models from providers such as Anthropic and OpenAI to address business intelligence and process automation needs.
Use development augmentation tools such as GitHub Copilot, Claude Code, and Codex to support planning, design, and development.
Build reusable AI components, SDKs, and engineering frameworks.
Use databases such as MongoDB and Databricks to store and process data.
Optimize AI infrastructure, inference pipelines, and orchestration workflows for availability, resilience, and operational efficiency.
Stay current with emerging AI technologies, frameworks, and best practices, and recommend capabilities that can enhance Mission’s AI strategy.
Monitor production AI systems, troubleshoot issues, and continuously improve solution quality and business outcomes.