Description

Design and build production-ready AI applications, multi-agent workflows, and scalable RAG systems using LLMs and Agentic AI frameworks.

This role is hybrid.

Responsibilities

• Build multi-agent workflows using LangChain, LangGraph, and Google ADK to orchestrate complex AI tasks.
• Develop scalable RAG-based applications integrated with Vector Databases and enterprise systems via REST APIs and Kafka.
• Ship production-ready AI services using Python, FastAPI, Docker, and Kubernetes on GCP or AWS.
• Implement monitoring, logging, evaluation, and governance for AI applications using OpenTelemetry and Grafana.
• Maintain automated CI/CD pipelines with GitHub Actions and Cloud Build, while mentoring developers on AI-first engineering practices.

Required Skills

• 10+ years of software engineering experience with a Bachelor's degree.
• Strong proficiency in Python, FastAPI, and AsyncIO.
• Hands-on experience with LangChain, LangGraph, and LLM integration (Vertex AI, AWS Bedrock, OpenAI APIs).
• Deep knowledge of RAG architectures and Vector Databases.
• Experience deploying containerized services with Docker and Kubernetes.
• Proficiency with CI/CD tools including GitHub Actions and Cloud Build.
• Experience with message streaming using Kafka and cloud services (GCP Pub/Sub, AWS).
• Familiarity with databases such as PostgreSQL, MongoDB, and Redis.

Preferred Skills

• Experience with Terraform for infrastructure as code.
• Background in building reusable AI platform components for prompt orchestration and agent frameworks.

Key Skills

Education

Bachelor's degree