Back
Mid-level popular AI role in Bangalore with a 3+ years requirement increases candidate density and competition.
LLM, prompt engineering, and RAG skills transfer across industries, though domain-specific data/regulatory experience helps.
Explicit 3+ years plus mandatory LLM harness, vector DB, and production engineering skills increase filter strictness.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own end-to-end delivery of AI productization projects as the AI engineer on Strike Teams, focusing on harness and prompt engineering for production features using LLMs.
Build and maintain complex LLM harnesses including agent loops, tool integrations, prompt iteration, and retrieval-augmented generation (RAG) pipelines ensuring quality and accuracy.
Collaborate with AI Architects and senior engineers on architectural decisions and assist in supporting AI tasks such as data parsing, embeddings, accuracy validation, and light ML work.
Bachelor's or Master's degree in Computer Science, Data Science, Statistics, or related technical field.
Minimum 3+ years of AI or data science experience with hands-on LLM-based application development.
Proficiency in Python and experience with AI frameworks (e.g., LangChain, LlamaIndex) and vector databases (e.g., OpenSearch, Pinecone).
Experience in building LLM harnesses, prompt engineering, and production-quality clean code with CI/CD practices.
Experienced in building and iterating agent harnesses and prompt libraries with a strong analytical and experimentation mindset.
Capable of operating in a collaborative, cross-functional Strike Team alongside AI Architects and senior engineers, with ability to contribute technical ideas and escalate as needed.
Comfortable with working on RAG pipelines, embeddings, and integrating diverse AI tooling in production environments, with some knowledge or interest in regulated or document-heavy domains (insurance/finance) preferred.