Data Scientist-Applied AI Engineer

Talent Corner Hr Services; Mumbai; On-site; INR 2,500,000 - 4,200,000; Full time

Job summary

Talent Corner Hr Services is seeking an Applied AI Engineer in Kurla, Mumbai to build real-world AI apps powered by LLMs. You will integrate LLMs into production systems, design scalable RAG pipelines, and orchestrate autonomous AI workflows with LangGraph and Google ADK.

You will implement production-grade AI APIs, optimize performance, and collaborate with product, data and engineering teams to deliver reliable, high-quality AI solutions.

Qualifications

• Hands-on experience building production-grade AI applications with LLMs.
• Experience designing retrieval pipelines and RAG architectures.
• Proficiency in Python, FastAPI, and deploying AI services.

Responsibilities

• Integrate LLMs into backend applications, APIs and production systems.
• Build and optimize RAG pipelines using vector stores and embeddings.
• Design agentic AI workflows with LangGraph and Google ADK.
• Develop multi-step, tool-using AI agents and scalable microservices.
• Collaborate with product and data teams to translate requirements into AI solutions.

Skills

LLM integration

RAG pipelines

Backend development

Python

FastAPI

LangGraph

LangChain

Vector databases

Prompt engineering

Troubleshooting

Education

Bachelor's or higher in CS/EE/Math

Tools

LangGraph

Google ADK

LangChain

Pinecone / FAISS / Weaviate / Milvus

Python / FastAPI

Job description

Data Scientist-Applied AI Engineer

Experience: 35 Years

Job location : Kurla, mumbai

Male candidates prefered

Role

We are looking for an Applied AI Engineer who can build real-world applications powered by Large Language Models (LLMs). The role focuses on integrating LLMs into production systems, building scalable RAG and agentic AI workflows, and writing efficient, high-performance backend code.

The ideal candidate should have hands-on experience building and deploying production-grade AI applications, LLM-powered APIs, RAG pipelines, and autonomous/agentic workflows using technologies such as LangGraph, Google ADK, LangChain, vector databases, embeddings, and Python/FastAPI.

Key Responsibilities

• Integrate Large Language Models (LLMs) into backend applications, APIs, and production systems.
• Build RAG (Retrieval Augmented Generation) pipelines using embeddings, vector databases, semantic search, document retrieval, and reranking.
• Design and implement agentic AI workflows using frameworks such as LangGraph and Google ADK (Agent Development Kit).
• Build multi-step, stateful, tool-using, and autonomous AI agents.
• Integrate LLMs with tools, APIs, databases, external services, and enterprise systems.
• Design and implement scalable AI workflows and orchestration pipelines.
• Develop production-grade AI-powered APIs and microservices.
• Optimize performance, latency, scalability, reliability, and cost of AI-powered services.
• Debug and troubleshoot complex issues across application logic, backend services, APIs, LLM integrations, RAG pipelines, vector retrieval, and agent workflows.
• Implement effective prompt engineering and context management strategies.
• Evaluate and improve LLM and AI-agent performance, accuracy, reliability, and response quality.
• Collaborate with product, frontend, data, and engineering teams to convert business requirements into scalable AI solutions.

Required Skills

• Strong experience integrating LLMs into production applications.
• Hands-on experience with RAG architectures and vector-based retrieval systems.
• Strong understanding of embeddings, semantic search, vector search, document retrieval, chunking, and retrieval pipelines.
• Experience building AI/agentic workflows using LangGraph, Google ADK, or similar AI orchestration frameworks.
• Strong understanding of agent architecture, state management, workflow orchestration, tool/function calling, and multi-step reasoning workflows.
• Strong backend programming skills in Python; FastAPI preferred.
• Experience working with LLM APIs such as OpenAI, Google Gemini, Anthropic Claude, or similar models.
• Hands-on experience with prompt engineering and context engineering.
• Experience working with vector databases such as Pinecone, FAISS, Chroma, Weaviate, Milvus, or similar technologies.
• Ability to write clean, efficient, scalable, maintainable, and high-performance code.
• Strong debugging, troubleshooting, analytical, and problem-solving skills.

Preferred Skills

• Experience building AI-powered APIs, backend services, and microservices.
• Experience with LangGraph, Google ADK, LangChain, LlamaIndex, or similar AI/agent frameworks.
• Experience with cloud platforms such as Google Cloud Platform (GCP), Amazon Web Services (AWS), or Microsoft Azure.
• Experience with cloud-based AI/LLM services such as Google Vertex AI, Amazon Bedrock, Azure OpenAI, or equivalent platforms.
• Familiarity with prompt engineering, embeddings, context engineering, and AI evaluation.
• Experience with LLM evaluation, observability, monitoring, tracing, and performance optimization.
• Knowledge of AI/LLM guardrails, hallucination mitigation, response validation, and reliability techniques.
• Experience with Docker, CI/CD, Git, and production deployment.
• Familiarity with REST APIs, asynchronous programming, databases, caching, message queues, and distributed systems.
• Understanding of production security, authentication/authorization, API management, and scalable service architecture.
• Experience deploying and operating production-grade GenAI/LLM applications.