AI Tech Lead

Magicbricks; Dadri; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Magicbricks seeks a senior AI/ML Architect to lead the design and development of AI/ML and GenAI platforms. You will build production-grade LLM applications, RAG pipelines, and multi-agent systems, driving scalable vector search architectures and embedding/inference optimizations.

You will mentor engineers, review technical work, and provide architectural direction across AI initiatives to ensure high quality and cost-effective delivery.

Qualifications

• Experience architecting GenAI/LLM systems at scale.
• Proven ability to translate business problems into AI solutions.
• Strong object-oriented design and system architecture skills.

Responsibilities

• Lead architecture and development of AI/ML and GenAI products.
• Build production-grade LLM apps, RAG pipelines and multi-agent systems.
• Design scalable RAG and vector search architectures and optimize performance.
• Evaluate LLMs and AI platforms balancing quality, latency and cost.
• Mentor engineers and provide technical direction across AI initiatives.

Skills

GenAI & LLM

Python

Node.js/TypeScript

REST APIs

Docker

Kubernetes

Distributed Systems

GPU/CUDA

Cloud Platforms

LangChain/LangGraph

Vector Databases

Education

Bachelor's/Master's in CS/Engineering/AI/ML/Data Science

Tools

LangGraph

LangChain

LlamaIndex

Langfuse

Qdrant

FAISS

Ollama

Job description

Role & responsibilities

Lead the architecture, design and development of AI/ML and Generative AI products and platforms.

Build production-grade LLM applications, RAG pipelines, AI Agents and multi-agent systems.

Design scalable RAG and Vector Search architectures, covering ingestion, embeddings, retrieval, reranking and context optimization.

Evaluate and integrate LLMs, open-source models and AI platforms, balancing quality, latency, cost, privacy and scalability.

Drive model fine-tuning, GPU inference, model serving and performance optimization for production workloads.

Establish LLM evaluation, observability and monitoring practices to continuously improve AI quality and reliability.

Design highly scalable, reliable and cost-efficient AI services across AWS, Azure and/or Google Cloud.

Mentor engineers, conduct technical reviews and provide technical direction and architectural leadership across AI initiatives.

Technical Skills

GenAI / LLM / Agents: LLMs, Open-Source Models, Prompt Engineering, RAG, Embeddings, Reranking, Transformers, AI Agents, Agentic & Multi-Agent Workflows.

Frameworks & Evaluation: LangGraph, LangChain, LlamaIndex, Langfuse or equivalent.

Vector Search: Qdrant, FAISS or similar Vector Databases; semantic/hybrid search and retrieval optimization.

Models & Infrastructure: Ollama, Fine-tuning, LoRA, GPU/CUDA, Model Serving, Inference Optimization.

Cloud & Platforms: AWS Bedrock, Google Vertex AI / Agent platforms, Azure AI / Agent platforms, OpenAI platforms, AWS/Azure/GCP.

ML / Computer Vision: CNNs, Ensemble Models, OCR, OpenCV, Face Similarity/Search at Scale, Image & Document Processing.

Engineering: Strong Python and/or Node.js/TypeScript, REST APIs, Microservices, Docker, Kubernetes, Distributed Systems, Queues, Databases, Caching, CI/CD, Monitoring and System Design.

Strong understanding of scalability, high availability, performance, security and cost optimization for production AI systems.

Preferred candidate profile

79 years of experience in Software Engineering / AI/ML, with significant hands‑on experience building production AI/ML or GenAI systems.

Proven ability to take AI solutions from POC production scale.

Strong system design, architecture and problem-solving skills.

Experience leading technical initiatives and mentoring engineers.

Bachelor's/Master's degree in Computer Science, Engineering, AI/ML, Data Science or related field preferred.