SDE-2 Gen AI

Postion- SDE-2 (Gen AI)

Role Summary:

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 tooling.

Responsibilities:

• Integrate LLM APIs into chatbots, virtual assistants, and backend services.
• Build and maintain prompt chains and tool-augmented agents using frameworks like LangChain
• Design and implement retrieval-augmented generation (RAG) systems using vector databases
• Develop middleware and backend logic to support dynamic, multi-turn conversational flows. (Applicable for SDE3)
• Work with embedding models to create semantic search and memory systems
• Optimize token usage, context management, and response quality.
• Implement function calling / tool usage features for LLMs to interface with real APIs or business systems.
• Monitor and log conversations for evaluation and improvement (e.g., response quality, latency, token usage).
• 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 technologies.
• Provide mentorship to mid/junior-level team members.

Required Technical Skills:

• Proficient in Python or Node.js/TypeScript.
• Exposure to MEAN Stack development concepts for end-to-end application
• Experience working with REST APIs, Webhooks, OAuth.
• Familiarity with LLM APIs
• Strong hands-on knowledge of:
• LangChain, Langwatch
• Prompt engineering
• Function calling / tools / agents
• Awareness of MultiAgent Architecture
• Working with embedding models and vector search engines.
• Understanding of context windows, chunking, and memory strategies.
• Experience with text classification, NER, summarization, semantic search.