Location: Bangalore (Hybrid)

ROLE SUMMARY

Engineer, you will own the architecture and delivery of enterprise-grade GenAI systems that integrate large language models (LLMs), multi-agent workflows, and embedding-powered retrieval solutions. You will guide engineering pods, define standards,

and drive innovation through scalable, production-ready intelligent applications.

Core Responsibilities

- Architect GenAI systems using LLM APIs, agent orchestration frameworks, and embedding pipelines at scale
- Design autonomous agent workflows with context management and multi-agent coordination
- Optimize performance, latency, and accuracy through prompt strategies and retrieval layers
- Lead solution reviews, enforce governance, and ensure alignment with security protocols




- Collaborate with product and platform teams to define reusable patterns and scalable AI capabilities
- Mentor engineers on design principles, reliability, and prompt lifecycle management

Required Skills

- 4–8+ years in AI/ML engineering with focus on GenAI applications
- Robust expertise in Databricks (Delta Lake, Spark SQL, PySpark) and Snowflake for scalable data/AI solutions
- Proficiency in Python (v3.11+), LLM APIs (OpenAI, LangChain, LangGraph)
- Hands-on experience with containerization, CI/CD, and cloud-native delivery (Azure preferred)
- Knowledge of agent orchestration, prompt optimization, and observability frameworks
- Deep understanding of foundational LLM models and their utility

📌 Sr AI Engineer (Bengaluru)
🏢 Xpheno
📍 Bengaluru