Senior AI Developer

Bupa; Gurugram District; Sur place; INR 3 500 000 - 5 500 000; Plein temps

Résumé du poste

Bupa is seeking an experienced Lead AI Engineer to design and deliver production-grade generative AI, LLM, RAG, and agentic AI solutions. You will mentor teams while shaping scalable AI architectures and advancing MLOps practices across cloud deployments.

You will architect end-to-end GenAI systems, integrate diverse LLMs, and build robust AI services with Python, FastAPI, and containerized microservices. A strong leadership profile is essential for guiding engineers and ensuring best practices.

Qualifications

• 8–12 years of software/AI engineering experience.
• Strong Python programming skills and hands-on generative AI/LLM experience.
• Deep knowledge of RAG architectures, agentic AI, and multi-agent systems.
• Experience with LangChain/LangGraph or equivalent frameworks.

Responsabilités

• Design and develop scalable GenAI and LLM-powered enterprise apps.
• Architect and implement advanced RAG pipelines (embedding, retrieval, re-ranking, eval).
• Build agentic AI and multi-agent systems using LangChain, LangGraph, AutoGen or Semantic Kernel.
• Integrate LLMs (OpenAI, Azure OpenAI, Claude, Gemini, etc.) and manage AI services.
• Develop microservices with Python and FastAPI; deploy on Docker/Kubernetes.
• Work with vector DBs (FAISS, Pinecone, Weaviate, Milvus, Azure AI Search).
• Implement prompt engineering, tool calling, memory and orchestration.
• Establish ML/LLMOps pipelines, CI/CD, monitoring and production deployment.
• Address AI security, guardrails, and LLM safety; lead code reviews and architecture.

Connaissances

Python programming

Generative AI / LLMs

RAG architecture

AI agents / multi-agent systems

LangChain / LangGraph

Vector databases

Cloud platforms (Azure / AWS / GCP)

MLOps / LLMOps

System design

Mentoring / technical leadership

Docker / Kubernetes

FastAPI / REST APIs

Outils

FAISS

Pinecone

Weaviate

Milvus

Azure AI Search

Hugging Face Transformers

PyTorch / TensorFlow

MLflow / Kubeflow

Terraform

CI/CD

Description du poste

We are looking for an experienced Lead AI Engineer to lead the design and development of production-grade generative AI, LLM, RAG, and agentic AI solutions. The ideal candidate should have strong hands-on experience in Python, LLMs, RAG architecture, AI agents, LangChain/LangGraph, vector databases, cloud, and MLOps, along with the ability to design scalable AI systems and mentor engineering teams.

Responsibilities:

• Design and develop scalable GenAI and LLM-powered applications for enterprise use cases.
• Architect and implement advanced RAG pipelines, including document processing, embeddings, retrieval, re-ranking, and evaluation.
• Build agentic AI and multi-agent systems using frameworks such as LangChain, LangGraph, AutoGen, or Semantic Kernel.
• Integrate LLMs such as OpenAI, Azure OpenAI, Claude, Gemini, or open-source LLMs.
• Develop AI services and microservices using Python and FastAPI.
• Work with vector databases such as FAISS, Pinecone, Weaviate, Milvus, or Azure AI Search.
• Implement prompt engineering, function/tool calling, structured outputs, memory, and agent orchestration.
• Build and maintain LLM evaluation and monitoring frameworks to improve accuracy, relevance, safety, and reliability.
• Deploy AI solutions on Azure/AWS/GCP using Docker and Kubernetes.
• Establish and improve MLOps/LLMOps pipelines, CI/CD, model monitoring, and production deployment practices.
• Work on AI security, responsible AI, guardrails, prompt injection prevention, and LLM safety.
• Drive technical architecture, code reviews, engineering best practices, and system design.
• Mentor engineers and provide technical leadership across AI initiatives.

Requirements:

• 8-12 years of software/AI engineering experience.
• Strong Python programming.
• Hands-on generative AI/LLM experience.
• Strong RAG architecture and implementation experience.
• Experience with Agentic AI / AI Agents / Multi-Agent Systems.
• Good to have: LangChain / LangGraph or equivalent agent frameworks.
• Experience with Vector Databases.
• Nice to have: LLM APIs such as OpenAI / Azure OpenAI / Claude / Gemini.
• Experience in FastAPI / REST APIs / Microservices, Docker, and Kubernetes.
• Experience with at least one major cloud platform: Azure, AWS, or GCP.
• Understanding of MLOps / LLMOps.
• Strong knowledge of AI system architecture and scalability.
• Good technical leadership and mentoring experience.
• Good to have: LlamaIndex, AutoGen, Semantic Kernel, Hugging Face Transformers, PyTorch / TensorFlow, MLflow / Kubeflow, Terraform and CI/CD, LLM evaluation and observability tools, AI red teaming / AI security, OWASP LLM Top 10 / NIST AI RMF, Fine-tuning / LoRA / QLoRA.
• Knowledge graphs and hybrid search.