AI Engineer (Up to 50LPA)

Role Overview

This is a founding engineering role for a VC-backed health-tech, AI, and wearable startup. You will work directly with the founders to design, build, deploy, and scale production-grade AI systems used by real customers, moving beyond prototypes to real-world multi-agent architectures and RAG pipelines.

Responsibilities

• Design, build, and deploy production-grade LLM applications and conversational AI systems
• Build multi-agent workflows using frameworks such as LangGraph or CrewAI
• Develop production RAG systems using vector databases and hybrid retrieval architectures
• Optimize inference latency, GPU utilization, memory consumption, and LLM serving costs
• Build reliable model serving infrastructure with monitoring, observability, evaluations, retries, and guardrails
• Work on real-time AI applications involving streaming, speech (STT/TTS), or voice agents
• Design scalable backend services and APIs supporting AI workloads
• Collaborate with product and engineering teams to rapidly ship AI features into production

Requirements

• 2+ years of software engineering or AI engineering experience
• Strong hands-on experience building production LLM applications
• Experience deploying RAG systems into production
• Experience with vector databases such as Pinecone, pgvector, Weaviate, Chroma, or FAISS
• Experience with LangChain, LangGraph, or LlamaIndex
• Strong understanding of transformers, embeddings, prompt engineering, and evaluation methodologies
• Experience building model serving infrastructure and production ML systems
• Strong backend engineering skills (Python preferred)
• Experience with cloud platforms (AWS/GCP/Azure), Docker, and scalable backend architecture

Skills

• Python
• LangChain
• LLM
• AWS
• Vector Databases