Full Stack Developer

Company Description

Afficiency is a rapidly growing Insurtech startup whose mission is to provide life insurance to everyone on the platforms they already trust. Located in NYC, we design life insurance products that can be purchased entirely digitally and can be easily embedded into distribution platforms or with agents who sell insurance. The company is experiencing rapid growth and is well-funded. We are looking for new team members to join us on our journey to shake up the life insurance industry. We need individuals who bring passion, curiosity, and a desire for excellence.

Job Description

We are seeking a highly skilled Full Stack Developer to design, develop, and deploy AI-driven digital solutions for Life Insurance business applications. The ideal candidate will possess strong full-stack development expertise along with hands-on experience in AI technologies, agentic workflows, prompt engineering, and Large Language Model (LLM) integrations.

This role will focus on building real-time AI-powered applications that enhance customer experience, underwriting, servicing, claims processing, agent productivity, knowledge management, and operational efficiency.

The successful candidate will work closely with business stakeholders, solution architects, data engineers, and digital product teams to deliver enterprise-grade AI solutions.

This role is for someone who is based in the NYC Metro Area, passionate about building real-world GenAI applications and bringing them into production, while continuously improving performance, reliability, and user outcomes.

Qualifications

Responsibilities

AI & Prompt Engineering

• Design, develop, and optimize prompts for Large Language Models (LLMs) including OpenAI Codex, GPT, Claude, Gemini, and other enterprise AI platforms.
• Build AI-powered workflows, copilots, virtual assistants, and intelligent agents for insurance business processes.
• Develop Retrieval-Augmented Generation (RAG) solutions using enterprise knowledge repositories and policy documentation.
• Implement prompt testing, evaluation, and optimization frameworks to improve accuracy, consistency, and reliability.
• Design agent-based solutions using tools, skills, plugins, function calling, workflows, and orchestration frameworks.
• Create reusable prompt libraries and AI solution accelerators.
• Monitor AI performance metrics and continuously improve model outcomes.

Application Development

• Design and develop modern web applications using React.js and related frontend technologies.
• Build RESTful APIs and microservices using Python Flask.
• Integrate AI services into enterprise digital applications.
• Develop real-time applications supporting customer service, underwriting, policy servicing, and claims workflows.
• Implement authentication, security, and scalability best practices.

Data & Integration

• Connect AI applications to enterprise systems through APIs and service layers.
• Work with structured and unstructured data sources supporting AI use cases.

Architecture & Delivery

• Participate in AI solution architecture and technology selection.
• Conduct proof-of-concepts and rapid prototypes.
• Collaborate with cloud, data, and application teams.
• Follow DevOps, CI/CD, and Agile development practices.
• Maintain documentation, technical specifications, and AI governance controls.

Education

• Bachelor’s Degree in Computer Science, Information Technology, Engineering, Data Science, or related discipline.

Experience

• Minimum 4+ years of software engineering experience.
• Minimum 2+ years developing AI-powered applications or Generative AI solutions.
• Experience in Life Insurance, Financial Services, or regulated industries is highly preferred.

Technical Skills / Exposure

Front-End Development

• React.js
• JavaScript / TypeScript
• HTML5 / CSS3
• Responsive UI development

Backend Development

• Python
• Flask API Development
• REST APIs
• Microservices Architecture

Database Technologies

• SQL Server, PostgreSQL, MySQL, or Oracle
• Database design and optimization
• Query performance tuning

AI & Generative AI

• Prompt Engineering
• Large Language Models (LLMs)
• OpenAI GPT/Codex
• Anthropic Claude
• Google Gemini
• AI Agents and Agentic Workflows
• RAG (Retrieval Augmented Generation)
• Vector Databases
• Embeddings
• Fine-Tuning Concepts
• Model Evaluation Techniques
• Tool Calling and Function Calling

AI Frameworks & Tools

• Claude…