Back
Mid-level metro AI platform role at a strong brand with broad full-stack and LLM requirements.
Requires specialized LLM, embeddings, semantic search and GCP experience, making cross-industry transferability limited.
Explicit 5+ years plus mandatory LLM, GCP, Python, vector search and full-stack stack increases filter strictness.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Drive design and implementation of core AI capabilities within an Intelligent Data Analytics Platform focusing on multi-agent orchestration, natural language-to-SQL generation, and semantic data discovery.
Write production-grade code across full stack (backend APIs and frontend interfaces) and develop reusable AI components, implementing LLM-powered workflows and semantic search.
Own features end-to-end including architecture design, coding, deployment, monitoring, and troubleshooting while setting engineering standards and anchoring the technical team.
5+ years of professional software engineering experience with strong hands-on coding.
Experience building AI-powered applications or working with LLM-based systems in production.
Proficiency in Python (primary), TypeScript, Angular/React, and backend frameworks such as FastAPI.
Work Experience Required: 5+ years; Location: Chennai, India (On-site).
Experienced individual contributor capable of owning complex, end-to-end AI software features involving architecture and implementation depth.
Familiar with multi-agent AI architectures, LLM integration, and semantic search including vector embeddings and retrieval optimization.
Comfortable working with full-stack development on cloud platforms (GCP, BigQuery, Vertex AI) and applying engineering best practices to solve hard technical challenges.