AI Engineer, Agentic Systems (Quality Engineering)

Overview

Build and ship agentic AI systems for automated testing and enterprise workflows across Salesforce, SAP, and custom IT platforms. The role focuses on LLM orchestration, tool calling, RAG, integrations, quality evaluation, safety, and observability.

What you'll do

• Develop agent workflows with LangGraph, ADK, LangChain, AutoGen, or CrewAI.
• Connect agents to Salesforce, SAP, and custom applications through APIs, webhooks, and queues.
• Build context-grounding and RAG pipelines using vector stores.
• Create tool definitions, JSON schemas, and MCP tools for traceable execution.
• Develop evaluation suites, guardrails, approval handoffs, and human-in-the-loop workflows.
• Instrument agents with tracing and metrics for performance and cost analysis.
• Collaborate with architects, QE leads, product managers, and security teams.

What you'll need

• 1–4 years of professional software engineering experience or equivalent demonstrable capability.
• Strong Python or TypeScript/Node.js skills.
• Experience building and consuming REST APIs, using relational databases, and handling asynchronous processing.
• Hands-on experience with LLM APIs, prompting, tool calling, and structured outputs.
• At least one end-to-end agent or retrieval pipeline.
• Experience with Git and automated build and test pipelines.
• B.E., B.Tech, or M.Tech in a related technical field, or equivalent practical experience.

Nice to have

• Production AI agents or LLM feature deployment experience.
• Experience with enterprise applications, vector databases, advanced retrieval, MCP, cloud, DevOps, or test automation.

Details

• Location: Bangalore, India.
• Work from the office full time.