Sign up with

Already have an account? Log in here

Need some help?
Talk to us at +91 7670800001

Consultant - Python Developer with Gen AI at KPMG Global Services

Bengaluru, karnataka, India -

Full Time

Start Date

Immediate

Expiry Date

19 Jul, 26

Salary

0.0

Posted On

20 Apr, 26

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Python, API Development, LLM Integration, FastAPI, Flask, RESTful APIs, WebSockets, Kafka, Pub/Sub, Microservices, LangChain, LangGraph, CrewAI, AutoGen, RAG, Agentic AI

Industry

Business Consulting and Services

Description

Responsibilities: * Overall experience of 4+ years using Python with API development and 2+ years of experience in integrating LLM * Hands-on experience in developing RESTful APIs and WebSockets using Python frameworks preferably using FastAPI/Flask * Implement event-driven architectures (e.g., Kafka, Pub/Sub) for low-latency data processing * Hand-on experience in designing. implementing and deploying micro service architecture based application * Troubleshoot and resolve backend issues, optimizing application performance and ensuring reliabilityl9iu * Stay updated with industry trends and best practices in backend development. * Leverage GenAI libraries like LangChain, LangGraph, CrewAI, AutoGen etc to build Agentic AI Applications * Integrate various LLM like Gemini, OpenAI, Claude etc. * Experience in implementing RAG based architecture * Monitor and optimize the performance of application Good to have Skills: * Experience in containerizing the application and hosting on Kubernetes * Ability to fine-tune base LLM * Experience in setting up data pipelines for model training and real-time inference * Experience with Azure/AWS/GCP Cloud Education Qualification: * BE / B.Tech / MCA

Responsibilities

The consultant will design and deploy microservice-based applications while integrating LLMs and GenAI libraries to build agentic AI solutions. They are also responsible for implementing event-driven architectures and optimizing backend performance for low-latency data processing.