L2 Engineer - Coach
Core
Design, develop, and deploy scalable backend services and production-grade Generative AI applications using TypeScript/JavaScript and AWS Serverless.
Role type
Mid-level backend engineer specializing in Generative AI and LLM integration
Builds
Cloud-native AI applications, RAG solutions, and real-time communication systems
Domain
Cloud infrastructure + Generative AI
Deliverable
production ML models
Required skills
TypeScript/JavaScript, AWS Serverless (Lambda, API Gateway, DynamoDB, VPC), LLM integration, RAG architectures, prompt engineering, LLM evaluation, vector databases, REST APIs, microservices, WebSockets, automated testing, CI/CD
Preferred skills
AI agent frameworks, AI evaluation frameworks (LangSmith, Ragas), AI observability, LLM cost/latency optimization, multi-agent systems
Technologies
AWS, OpenAI, Anthropic, Gemini, LangChain, LangGraph, LlamaIndex, Semantic Kernel, Vector databases
Responsibilities
Design and implement REST APIs and event-driven architectures; Engineer effective prompts and AI workflows; Conduct LLM evaluations and benchmarking; Implement AI observability and monitoring; Build robust automated testing frameworks; Collaborate with Product and Engineering teams to deliver AI-powered features
Seniority
Mid-level, hands-on IC
