AI Engineer (LLMs - Agentic AI - Orchestration - RAG)

Knowledge Foundry; Bengaluru; On-site; INR 3,000,000 - 6,000,000; Full time

Job summary

Knowledge Foundry is seeking an experienced AI Platform Engineer to build the Agentic Orchestration Layer powering next‑generation insurance AI platforms. You will develop enterprise-grade AI agents, multi‑agent orchestration workflows, RAG pipelines, context/memory services, and AI tool integrations with Guidewire services.

We value hands-on experience with LLM-powered apps, Agentic AI systems, and production-grade GenAI solutions.

Qualifications

• Strong hands-on experience building and deploying LLM-powered applications.
• Experience with enterprise AI agents and multi-agent orchestration workflows.
• Knowledge of RAG pipelines, embeddings, vector databases, and tool integrations.

Responsibilities

• Design and build multi-agent AI systems and orchestration workflows.
• Develop enterprise-grade RAG pipelines and context/memory services.
• Build AI tools, function calling, tool calling, and agent integrations.
• Integrate AI applications with enterprise APIs and Guidewire services.
• Create and maintain prompt libraries, evaluation frameworks, and AI guardrails.
• Optimize AI systems for latency, accuracy, reliability, and inference cost.
• Collaborate with Platform Engineering teams for production deployment and scalability.

Skills

Python

LLMs

Multi-agent systems

Agentic AI

Context & memory management

Prompt engineering

Production-grade AI

Tools

FastAPI

REST APIs

asynchronous programming

LangGraph

LangChain

Semantic Kernel

CrewAI / AutoGen

Pinecone

OpenSearch

FAISS

Amazon Bedrock

AWS Lambda

API Gateway

Step Functions

Git

Docker

Job description

About the Role :

We are looking for an experienced AI Platform Engineer for our US InsurTech Client to build the Agentic Orchestration Layer powering next-generation intelligent insurance platforms.

This is a hands-on engineering role focused on building enterprise AI agents, multi-agent orchestration workflows, RAG pipelines, context and memory services, and AI tool integrations. You will work on production-grade AI systems integrated with enterprise applications and Guidewire services.

If you have strong hands-on experience building and deploying LLM-powered applications, Agentic AI systems, and enterprise RAG solutions, we would like to hear from you.

Roles & Responsibilities :

• Design and build multi-agent AI systems and orchestration workflows.
• Develop enterprise-grade RAG pipelines and context/memory services.
• Build AI tools, function calling, tool calling, and agent integrations.
• Integrate AI applications with enterprise APIs and Guidewire services.
• Create and maintain prompt libraries, evaluation frameworks, and AI guardrails.
• Optimize AI systems for latency, accuracy, reliability, and inference cost.
• Collaborate with Platform Engineering teams for production deployment and scalability.

Required Skills & Experience :

• Strong programming experience in Python.
• Hands-on experience with FastAPI, REST APIs, and asynchronous programming.
• Strong experience with one or more AI orchestration frameworks such as:
• LangGraph
• LangChain
• Semantic Kernel
• CrewAI / AutoGen
• Strong understanding and hands-on experience with:
• Large Language Models (LLMs)
• Retrieval-Augmented Generation (RAG)
• Embeddings
• Vector databases
• Experience with vector technologies such as Pinecone, OpenSearch, or FAISS.
• Hands-on exposure to Amazon Bedrock, AWS Lambda, API Gateway, and Step Functions.
• Experience in prompt engineering, tool calling, function calling, and structured outputs.
• Working knowledge of Git and Docker.

Nice to Have :

• Guidewire experience.
• Insurance domain knowledge.
• Knowledge Graphs / GraphRAG experience.
• AI Security and Governance experience.

What We Are Looking For

We are particularly interested in engineers who have built real-world, production-grade GenAI applications.

The ideal candidate should be able to demonstrate hands-on experience in areas such as:

• Building end-to-end RAG systems.
• Designing stateful or multi-agent workflows.
• Integrating LLMs with enterprise APIs and external tools.
• Implementing context and memory management.
• Deploying and optimizing AI applications for production environments.
• Improving AI application accuracy, latency, reliability, and cost efficiency.