SDE-2 Gen AI

Position - SDE-2 (Gen AI)

About Simplilearn

Simplilearn is the world's #1 live online training company focused on digital skills. Founded in 2010, with offices in San Francisco, California, and Bangalore, India, and backed by the Blackstone Group, we drive talent transformation for over 500 global organizations, including Amazon, Bosch, Dell, and EY

.We are disrupting the talent development market with our one-of-a-kind online subscription product, Simplilearn Learning Hub+, which enables organizations to offer their workforce unlimited live and interactive learning led by experts, along with a comprehensive library of on-demand content and hands-on projects—all in one single plan

.Our award-winning content and curriculum, designed and updated by renowned industry and academic experts, cover all the digital skills required by organizations, including AI, ML, Data Science, Cyber Security, Software Engineering, Project Management, and more. We are authorized training partners for over 15 certification bodies, including PMI, PeopleCert, Scaled Agile, and industry partners of AWS, Microsoft, and more

.Our goal is to enable organizations to deliver a highly impactful and engaging learning experience to their workforce, driving talent transformation for business success

.We are looking for a hands-on SDET Tech Lead with strong expertise in Manual Testing, Playwright or Cypress Automation, and Jenkins-based CI/CD deployments. The role requires end-to-end quality ownership, automation strategy leadership, and seamless release management

.
Role Summar

y:As a GenAI Developer, you will work on building, integrating, and deploying cutting-edge Conversational AI systems using Large Language Models (LLMs). You'll be responsible for everything from prompt engineering to backend orchestration and scalable AI toolin

g.
Responsibiliti

• es:Integrate LLM APIs into chatbots, virtual assistants, and backend servic
• es.Build and maintain prompt chains and tool-augmented agents using frameworks like LangCh
• ainDesign and implement retrieval-augmented generation (RAG) systems using vector databa
• sesDevelop middleware and backend logic to support dynamic, multi-turn conversational flows. (Applicable for SD
• E3)Work with embedding models to create semantic search and memory syst
• emsOptimize token usage, context management, and response quali
• ty.Implement function calling / tool usage features for LLMs to interface with real APIs or business syste
• ms.Monitor and log conversations for evaluation and improvement (e.g., response quality, latency, token usag
• e).Partner with Product and various platform teams to identify, highlight, and integrate new opportunities, ensuring the timely delivery of pivotal projects leveraging LLM, RAG, and AI/Generative AI technologi
• es.Provide mentorship to mid/junior-level team membe

rs.
Required Technical Ski

• lls:Proficient in Python or Node.js/TypeScr
• ipt.Exposure to MEAN Stack development concepts for end-to-end applica
• tionExperience working with REST APIs, Webhooks, OA
• uth.Familiarity with LLM
• APIsStrong hands-on knowledge
• of:LangChain, Langw
• atchPrompt enginee
• ringFunction calling / tools / ag
• entsAwareness of MultiAgent Architec
• tureWorking with embedding models and vector search engi
• nes.Understanding of context windows, chunking, and memory strateg
• ies.Experience with text classification, NER, summarization, semantic sea