Description

Build and maintain Gen AI and LLM systems, managing production incidents and ensuring reliable integration across cloud and streaming infrastructure.

This role is on-site.

Responsibilities

• Design and implement Gen AI solutions using Python, focusing on prompting, guardrails, and RAG architectures.
• Manage production incidents, utilizing ServiceNow for tracking and Dynatrace/Splunk for monitoring and debugging.
• Integrate systems via REST APIs, handling authentication, tokens, and payload validation.
• Orchestrate deployments using Kubernetes, Helm, and ArgoCD, ensuring proper resource limits and config hygiene.
• Process streaming data with Kafka and Flink, and query BigQuery SQL for data requirements.

Required Skills

• 7+ years of experience in software engineering, with specific focus on AI/LLM systems.
• Strong proficiency in Python for building AI-driven applications and backend services.
• Hands-on experience with GCP, including IAM, project navigation, and service logs.
• Deep understanding of Kubernetes (Pods, deployments, kubectl) and Docker containers.
• Experience with streaming technologies like Kafka and Flink.
• Proficiency in SQL, specifically BigQuery SQL.
• Familiarity with CI/CD tools including Git, Helm charts, and ArgoCD.
• Experience with monitoring tools such as Dynatrace and Splunk.

Preferred Skills

• Experience working in agile development projects with sprint delivery focus.
• Ability to communicate effectively with customers and stakeholders regarding technical work.

Key Skills

Education

Any Graduate