Senior Staff Agentic AI Engineer

Overview

Build, ship, evaluate, and harden production LLM-powered agents and the platform they run on for the software delivery lifecycle. The role covers agentic systems spanning intake, design, coding, testing, release, operations, and value tracking, with humans directing the work and owning every gate.

What you'll do

• Design, build, and ship LLM-powered agents that execute intake triage, estimation, requirements, technical design, coding, testing, release, and operations work.
• Engineer dependable agent scaffolding using MCP tool use, agent-to-agent handoffs (A2A), event-driven orchestration, and deep Jira and enterprise system integration.
• Build on the enterprise AI platform, including the AI gateway, orchestration, audit, and access control, with security and privacy by design.
• Design and automate evaluation suites that measure agent output quality on every change and make passing evaluations the release gate for agents.
• Define guardrails, human-in-the-loop approval points, review thresholds, and escalation paths.
• Instrument agent behavior end to end for quality, latency, cost, and adoption; find failure patterns; and tune prompts, context, and configurations.
• Build knowledge layers using retrieval over process libraries, decision histories, code, and delivery data.
• Establish reusable prompt patterns, context standards, and agent configurations for adoption by other teams.
• Own agents through their full lifecycle, including instructions, context freshness, performance monitoring, feedback, and retirement.
• Contribute to the orchestrator, persona consoles, and dashboards that keep humans in command of agent-led delivery.
• Use agents to build agent systems and feed learnings back into the platform.
• Apply architecture, code quality, testing, CI/CD, and cloud-native design practices.

What you'll need

• 6+ years of professional software engineering experience, with a record of shipping and operating production systems.
• Hands-on experience building LLM-powered applications or agents, including prompt and context engineering, tool calling, retrieval, or multi-agent workflows.
• Experience designing evaluations for AI systems, or strong test-engineering instincts to apply to non-deterministic software.
• Strong proficiency in Python or TypeScript.
• Solid API, microservices, and event-driven architecture skills.
• Fluency with Git, automated testing, CI/CD, observability, and cloud platforms.
• Sound judgment about when to trust automation and when to demand human review.
• Communication skills to explain that reasoning.

Nice to have

• Experience with agent frameworks and protocols such as MCP, A2A, Anthropic or OpenAI APIs, Bedrock, Vertex, or LangGraph.
• Experience building developer platforms, orchestration systems, or SDLC tooling, including Jira, GitHub, or ServiceNow integration.
• Knowledge-engineering experience with retrieval systems, embeddings, or enterprise knowledge graphs.
• Experience taking AI features through security, privacy, and responsible AI review in an enterprise.
• Open-source contributions, technical writing, or internal platforms with devoted users.

Details

• Location: Bangalore Office BLS2.