AI Engineer

Luna Bearings; Hyderabad; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

Cornerstone OnDemand, Hyderabad-based, is seeking an AI Engineer to join our Workforce Intelligence team. You will build end-to-end backend features, implement an LLM integration layer, and contribute to RAG and semantic search architectures while delivering rich React/TypeScript frontends.

You will translate natural-language questions into validated analytics queries and collaborate with data science, product, and platform engineering to ship robust AI-powered solutions.

Qualifications

• 2-4 years of experience building production backend services in languages like Java, Python, or Go.
• Working experience with TypeScript and React, or willingness to work full-stack.
• Solid understanding of REST API design, distributed systems, and SOA.
• Experience integrating LLMs into production systems - prompt design, streaming, or structured output handling.

Responsibilities

• Build and own backend features - design, implementation, testing, code review, and production monitoring.
• Work on LLM integration layer: streaming AI responses, prompt engineering, structured output parsing, and response validation.
• Contribute to RAG and semantic search architecture - hybrid vector search, caching strategies, and data ingestion pipelines.
• Build rich, interactive frontend experiences in React/TypeScript that render AI-generated content in real time.
• Improve NL-to-SQL pipeline translating natural-language questions into validated analytics queries.
• Participate in architecture discussions, technical design reviews, and cross-team collaborations.

Skills

Backend development

Full-stack

API design

Cloud/AWS

LLM integration

Tools

React

TypeScript

Docker

Kubernetes

Job description

AlEngineer - India

Thisrole is Office Based, Hyderabad Office

Cornerstone OnDemand is looking for a motivated AI Engineer to join our Workforce Intelligence team. You'll work on an AI-powered assistant that helps managers and HR leaders understand their teams - surfacing skill gaps, career pathways, and organizational insights through natural-language conversations backed by LLMs and real-time analytics.
In this role, you'll build and ship features end-to-end across our backend and React/TypeScript frontend, working closely with data science, product, and platform engineering.

Inthis role, you will...

• Build and own backend features - design, implementation, testing, code review, and production monitoring.
• Work on our LLM integration layer: streaming AI responses, prompt engineering, structured output parsing, and response validation.
• Contribute to our RAG and semantic search architecture - hybrid vector search, caching strategies, and data ingestion pipelines.
• Build rich, interactive frontend experiences in React/TypeScript that render AI-generated content in real time.
• Improve our NL-to-SQL pipeline that translates natural-language questions into validated analytics queries.
• Participate in architecture discussions, technical design reviews, and cross-team collaborations.

You'veGot What It Takes If You Have...

• 2-4 years of experience building production backend services in any major language (Java, Python, Go, etc.).
• Working experience with TypeScript and React, or a strong willingness to work full-stack.
• Solid understanding of REST API design, distributed systems, and service-oriented architecture.
• Experience integrating LLMs into production systems - prompt design, streaming responses, or structured output handling.
• Experience with AWS services and containerized deployments (Docker, Kubernetes).
• Strong engineering fundamentals: you care about test coverage, code review quality, and observable, maintainable systems.

Extra dose of awesome if you have...

• Familiarity with vector databases or semantic search systems (Weaviate, Pinecone, pgvector, etc.).
• Experience with reactive or async programming patterns (WebFlux, SSE streaming, etc.).
• Exposure to analytics databases (ClickHouse, Snowflake, or similar).
• Familiarity with Redis for caching, session state, or pub/sub.
• Experience with monorepo tooling (Nx, Turborepo, etc.).Hands-on experience with prompt engineering, RAG architectures, or AI agent patterns

#LI-Onsite