L2 Engineer - Coach

<h3><strong>L2 Engineer – GenAI Focused</strong></h3><p><strong>Location:</strong> Pune</p><h3><strong>Summary</strong></h3><p>We are seeking a Mid-Level AI Engineer to join our team and contribute to the design, development, and deployment of modern AI-powered applications.

The ideal candidate will have strong expertise in <strong>TypeScript/JavaScript</strong>, <strong>AWS Serverless architecture</strong>, and experience building and operating <strong>production-grade Generative AI applications</strong>.</p><p>This role will focus on developing scalable backend services, integrating Large Language Models (LLMs), designing AI-powered workflows, evaluating model performance, and delivering reliable cloud-native solutions.</p><h3><strong>Responsibilities</strong></h3><ul><li>Design, develop, and maintain scalable backend services using <strong>TypeScript/JavaScript</strong></li><li>Build and operate cloud-native applications on AWS Serverless architecture using:</li><ul><li>API Gateway</li><li>Lambda</li><li>DynamoDB</li><li>VPC</li></ul><li>Design and implement REST APIs and event-driven architectures</li><li>Build and deploy production-grade Generative AI applications</li><li>Develop RAG-based solutions using vector databases, embeddings, and modern LLM frameworks</li><li>Engineer effective prompts and AI workflows to optimize application performance</li><li>Conduct LLM evaluations, benchmarking, and performance analysis</li><li>Implement AI observability, monitoring, and quality evaluation mechanisms</li><li>Work with WebSocket-based real-time communication systems</li><li>Build robust automated testing frameworks including:</li><ul><li>Unit Testing</li><li>Integration Testing</li></ul><li>Implement and maintain CI/CD pipelines and deployment workflows</li><li>Collaborate with Product, Engineering, and AI teams to deliver AI-powered features</li><li>Troubleshoot, debug, and optimize application performance and reliability</li><li>Contribute to architecture decisions and engineering best practices</li></ul><h3><strong>Required Qualifications</strong></h3><ul><li>3–6 years of professional software engineering experience</li><li>Strong expertise in <strong>TypeScript/JavaScript</strong></li><li>Hands-on experience with AWS Serverless services:</li><ul><li>API Gateway</li><li>Lambda</li><li>DynamoDB</li><li>VPC Networking</li></ul><li>Experience designing and building distributed backend systems</li><li>Strong understanding of REST APIs, microservices, and event-driven architectures</li><li>Experience with WebSockets and real-time communication systems</li><li>Strong experience with Unit Testing and Integration Testing</li><li>Experience building and supporting production-grade GenAI applications</li><li>Experience working with LLMs such as:</li><ul><li>OpenAI</li><li>Anthropic</li><li>Gemini</li><li>Open-source LLMs</li></ul><li>Experience with prompt engineering and prompt optimization techniques</li><li>Experience conducting LLM evaluations and measuring model performance</li><li>Familiarity with:</li><ul><li>LangChain</li><li>LangGraph</li><li>LlamaIndex</li><li>Semantic Kernel</li></ul><li>Experience with vector databases, embeddings, and RAG architectures</li><li>Strong software engineering fundamentals, design patterns, and system design skills</li><li>Excellent problem-solving and communication skills</li></ul><h3><strong>Preferred Qualifications</strong></h3><ul><li>Experience with AI agent frameworks and agentic workflows</li><li>Experience with AI evaluation frameworks such as LangSmith, Ragas, DeepEval, or equivalent</li><li>Familiarity with AI observability and monitoring platforms</li><li>Experience optimizing LLM cost, latency, and reliability</li><li>Exposure to multi-agent systems and advanced GenAI architectures</li></ul><h3><strong>Ideal Candidate Profile</strong></h3><p>We are looking for engineers who have already built and deployed GenAI solutions into production and can contribute immediately within our TypeScript-based AWS Serverless ecosystem.

Candidates with hands-on experience in LLM evaluations, prompt engineering, RAG architectures, WebSockets, and automated testing will be highly preferred.</p><p>&nbsp;</p>