Senior Full-Stack Developer

Location: In Office / Hybrid — Bengaluru Role Type: Full-time About the Team Cheerio is a no-code CRM & revenue management platform enabling businesses to retain customers like enterprise CRMs—at 1/20th the cost , with zero complexity . Available across web and mobile, we’re democratizing advanced customer management for millions of businesses globally. Join us as a founding engineer during our most explosive growth phase. About the Role We’re hiring a Technical Lead / Senior Full-Stack Developer with deep expertise in AI systems , modern full-stack engineering, and scalable distributed architectures. This is a hands-on, high-ownership role for someone who wants to build, architect, and lead from the front. You will: Own end-to-end system design , architecture, and tech decision-making Build and scale a high-volume platform powering AI-driven CRM automation Lead the integration and productionization of LLMs (OpenAI, Anthropic, Llama, etc.) Architect agentic AI workflows , orchestrators, and multi-agent systems Design and optimize pipelines using LangChain, LangGraph , and other orchestration frameworks Architect and query vector databases (Pinecone, Weaviate, Milvus, Chroma) for semantic search & retrieval Implement Retrieval-Augmented Generation (RAG) pipelines at scale Leverage embeddings, fine-tuning, model evaluation, and prompt engineering best practices Own scalable infra involving MongoDB , distributed services, caching, queues, and event systems Collaborate directly with founders on product & roadmap Hire, mentor, and scale a world-class engineering team Translate business goals into technical milestones with a bias for action What We’re Looking For Core Engineering Requirements 4+ years in MERN (MongoDB, Express, React, Node.js) Strong experience in system design , high-scale architectures, distributed systems Proven ability to scale MongoDB clusters and optimize high-throughput data pipelines Deep experience with CI/CD , containerization, and AWS or similar cloud stacks Prior leadership owning products/modules end-to-end Strong understanding of DevOps, microservices , and agile development Deep AI Expertise (Required) Hands-on experience building and deploying LLM applications in production Strong familiarity with LLM orchestration using: LangChain / LangGraph Haystack , LlamaIndex , or equivalent frameworks Proficiency with vector databases : Pinecone, Weaviate, Milvus, Qdrant, Chroma Experience designing RAG systems, semantic search, embeddings, chunking strategies Ability to build AI agents : Tool-using agents Multi-step reasoning and workflow automation Agentic planning and memory systems Knowledge of: OpenAI function calling , model routing, fallbacks, tool integration Prompt engineering , evaluation frameworks, LLM latency & cost optimization Fine-tuning , distilled models, adapters (LoRA/QLoRA), inference optimization Experience with LLMOps (monitoring, observability, model versioning) Understanding of Kafka / Redis / WebSockets for real-time AI pipelines Familiarity with transformer architectures , tokenization, and model performance limits Bonus Points Experience with MarTech / AdTech / CRM platforms Hands-on experience with: Elasticsearch / OpenSearch Event-driven systems (Kafka, AWS Kinesis, RabbitMQ) High-scale caching layers (Redis) Experience optimizing LLM cost/performance at scale Exposure to AI security , PII handling, data privacy & compliance Why Join Us Build a category-defining global SaaS product Work closely with founders and leadership Own meaningful product areas end-to-end Join a fast-moving team with a culture of trust, ownership, and speed