LLM Systems / AI Agent Engineer

📋 Description

• Build, deploy, and improve production AI agents using foundation models (e.g., AWS Bedrock).
• Design orchestration systems for tool calling, streaming, context mgmt, outputs, and agent
• Apply context-engineering to improve reliability and effectiveness of LLM/agent systems.
• Develop evaluation datasets and pipelines for tool selection, trajectories, and LLM-as-judge
• Establish production observability, tracing, and instrumentation for AI workloads.
• Contribute architectural assessment of orchestration layers and evaluate frameworks

🎯 Requirements

• 2+ years building production LLM agents with tool-calling loops, streaming, context mgmt, and
• Production experience with LangGraph, LangChain, or custom orchestration; solid agent architecture
• 1.5+ years of evaluation-driven development with datasets/pipelines for tool selection and
• 1+ year in LLM observability/trace instrumentation (Langfuse, OpenTelemetry, etc.); production
• 1+ year optimizing LLM costs via caching, model selection, routing; strong backend focus.
• 5+ years backend engineering with TypeScript/Node.js, PostgreSQL, and serverless AWS.

🎁 Benefits

• Fully remote, full-time role based in India with work-life balance benefits.
• Fixed working hours with region-specific IST shifts; no weekend work.
• Laptop provided day one; full medical insurance from start.
• Mentorship and access to professional communities; collaborative, growth-focused environment.
• Opportunity to own meaningful architectural direction in a small, specialized team.
• Long-term career growth where individual contributions are valued.