Senior LLM(Large Language Models) Engineer (RAG)

Role: LLM Engineer

Location: Bangalore(Hybrid)

Type: Fulltime

Job Description

Looking for a senior LLM Engineer who has solid experience doing production deployments. People

who have been developing solutions hands-on, not just building prototypes and POCs, we need an

end-to-end experience.

Must have:

Python development (3-4 years)

API Development with Fast API or Flask

Software Engineering: well versed with APIs, using WebSockets, doing production deployments

AWS services experience: working using services to spin up machines, EC2 machines, and deploy

their solution using AWS setup - could be SageMaker or simple EC2 machines.

AWS Architecture knowledge: if they develop something in Python, they should know how to

interact with AWS services, how to use the databases there, and how to use some inbuilt packages

as well.

Solid LLM/GenAI experience: anyone who has worked with this has probably used one of the main

frameworks such as Langchain, LlamaIndex and DSPy. They're not mandatory but they're a good

indicator of a solid experience. They must have experience with GenAI tools like Open AI,

Langchain, vector DB

Recent LLM hands-on experience (2 years): during the past 2 years they must have been working

with prompt engineering, implementing RAG

Familiarity with Kubernetes: Should be able to build pipelines, be familiar with containerizing and

creating API endpoints and then hand them over to DevOps engineers to take care of deployment

with Kubernetes. They won't be doing deployment.

Nice to have:

Azure

Experience fine tuning open-source models. Not as a hobby, but a serious thing that has been

deployed.