Back
Mid-level LLM-focused role in Bangalore at a known employer attracts many qualified applicants.
Skills are transferable across industries, though insurance domain knowledge is beneficial.
Explicit 3+ years plus several mandatory LLM/tool proficiencies increases screening rigor.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own the design, build, and maintenance of LLM harnesses and agent loops including tool/function calling, retries, and failure handling for AI product features.
Lead prompt engineering efforts: design, version, experiment, and evaluate prompts as key assets to improve AI feature accuracy and quality.
Build and operate Retrieval-Augmented Generation (RAG) pipelines and manage embedding/vector indexes to support production AI features, ensuring on-time delivery of AI-side Strike Team commitments.
Bachelor's or Master's degree in Computer Science, Data Science, Statistics, or related technical field.
3+ years of professional AI or data science experience involving LLM application development.
Strong Python programming skills including data science libraries (pandas, numpy, scikit-learn).
Experience with LLM harnesses and agent loop development using APIs (Anthropic, OpenAI, Bedrock) and at least one orchestration framework (LangChain, LlamaIndex, LangGraph) plus vector databases.
Experienced in prompt engineering with structured iteration, versioning, evaluation against datasets, and prompt library management.
Ability to write clean, production-ready, tested code following engineering best practices including Git and CI/CD workflows.
Skilled in AI feature accuracy validation, data analysis, error inspection, and iterative experimentation to improve model and pipeline performance.