Senior Applied AI Engineer

Job Details

Role Type: Full-Time
Location: Fully Remote (USA)
Reports To: VP of Product and Engineering

About This Role

We're seeking a Senior Applied AI Engineer to bridge the gap between cutting-edge AI capabilities and real-world product features that transform how we support students with learning differences. This role goes beyond traditional full-stack development—you'll be the architect of intelligent systems that leverage leading models to create meaningful experiences for educators, clinicians, and students.

As our AI specialist, you'll build production-ready agent systems, implement sophisticated tool-calling architectures, and ensure our AI features work seamlessly within our existing product ecosystem. You'll be at the forefront of applied AI, turning the latest advances into practical solutions that directly impact children's educational outcomes.

Seize this exciting opportunity to:

• Build and deploy AI agents that enhance clinical and educational workflows
• Architect intelligent features using the latest LLMs without reinventing the wheel
• Shape how AI is integrated across our entire product suite
• Work with both Python and TypeScript to create cohesive AI experiences
• Pioneer responsible AI practices in the sensitive EdTech/HealthTech space
• Collaborate with a passionate team dedicated to making a real difference

Technology Stack

• AI/LLM Providers: Anthropic Claude, Hugging Face, Vertex AI
• Agent Frameworks: LangChain, LangGraph, CrewAI, AutoGen
• Backend: NestJS (Express), TypeScript, FastAPI, Python
• Frontend: React, Material UI
• Databases: PostgreSQL with pgvector
• Infrastructure: Google Cloud Platform, Docker, GitHub Actions
• Monitoring: Sentry, Datadog, LangSmith for LLM observability

Key Responsibilities

• AI Agent Development

  • Design and implement production-ready AI agents using LangChain, LangGraph, and similar frameworks
  • Build sophisticated tool-calling systems that allow AI to interact with our application APIs
  • Develop multi-agent workflows for complex educational and clinical tasks
  • Create robust prompt engineering strategies and maintain prompt versioning
  • Implement RAG systems for contextual AI responses
  • Optimize agent performance for latency, cost, and accuracy

• Full-Stack AI Integration

  • Build Python-based AI services using FastAPI for model serving
  • Develop TypeScript/React components that seamlessly integrate AI features
  • Create real-time streaming interfaces for LLM responses
  • Implement secure API endpoints for AI functionality with proper authentication
  • Design fallback systems and graceful degradation for AI features
  • Build evaluation and testing frameworks for AI-powered features

• Compliance & Responsible AI

  • Ensure all AI implementations comply with FERPA and COPPA requirements
  • Implement privacy-preserving techniques for handling sensitive student data
  • Build audit trails and explainability features for AI decisions
  • Develop content filtering and safety mechanisms appropriate for K-12 environments
  • Create monitoring systems to detect and prevent AI misuse or harmful outputs
  • Collaborate with legal and compliance teams on AI governance policies

What We Need To See

• Required Qualifications

  • 5+ years of software engineering experience with at least 2 years focused on AI/ML applications
  • Strong proficiency in both Python and TypeScript/JavaScript
  • Production experience with LLM APIs (OpenAI, Claude, or similar)
  • Experience building and deploying AI agents or conversational AI systems
  • Demonstrated ability to implement RAG systems and vector databases
  • Strong understanding of prompt engineering and LLM limitations
  • Experience with modern web frameworks (React, NestJS, FastAPI)
  • Track record of shipping AI features to production at scale
  • Must be authorized to work in the US

• Required Technical Skills

  • AI/ML Frameworks: LangChain, LangGraph, or similar agent frameworks
  • LLM Integration: OpenAI API, Claude API, function calling, streaming responses
  • Vector Databases: Pinecone, Chroma, pgvector, or similar
  • Programming: Advanced Python (async, type hints), modern TypeScript
  • Databases: PostgreSQL, Redis, experience with embeddings and similarity search
  • API Design: RESTful APIs, GraphQL, WebSocket for real-time features
  • Testing: Unit testing for AI components, evaluation frameworks
  • Monitoring: LLM-specific observability tools (LangSmith, Weights & Biases)

Ways To Stand Out

• Knowledge of FERPA, COPPA, or HIPAA compliance in AI systems
• Published work or open-source contributions in applied AI/LLM space
• Experience with fine-tuning or deploying open-source models (Llama, Mistral)
• Background in education technology or healthcare technology
• Experience with real-time AI features (voice, video analysis)
• Knowledge of AI safety and alignment practices
• Contributions to prompt engineering communities or frameworks
• Experience with edge deployment of smaller models