Match Score
Against your primary resumeLogin to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Protocol Intelligence
Data-driven signals on your job's competitivenessNiche LLM/agent expertise reduces applicant pool, but Bengaluru metro and recognizable brand increase competition.
Specialized LLM, agent orchestration, and prompt-engineering requirements limit cross-industry transferability.
Explicit 6+ years, required LLM/agent experience and specific tech stack create strict filtering.
Job Description
Structured overview of role & requirementsAbout This Role
Develop, build, and ship AI-powered agentic applications and multi-agent workflows using Python and/or Node.js within established LLM orchestration frameworks.
Integrate and maintain agent connections to enterprise SaaS applications and other business systems using APIs, connector frameworks, and tool registries to support multiple business use cases.
Design, implement, and operate evaluation frameworks, test cases, and observability tools to measure agent behavior accuracy, hallucination rates, and guardrail compliance within an established architecture.
Minimum Requirements
6+ years of professional software engineering experience, including 1–2 years building with LLMs or agentic frameworks.
Strong proficiency in Python and/or Node.js for AI/backend development.
Experience with LLM providers (e.g., OpenAI, Anthropic), orchestration frameworks (LangChain, LangGraph), RAG pipelines, and prompt engineering.
Working knowledge of SQL/NoSQL databases and experience integrating agents/tools with enterprise applications via REST APIs or connector frameworks.
Ideal Candidate Profile
Experienced in designing and operating complex multi-step agentic system workflows within an established architecture rather than creating new architectures independently.
Practiced in building scalable AI applications combining LLMs, tool integrations, and contextual data management for enterprise environments.
Skilled in evaluation and debugging of AI agents including familiarity with safety controls, access-logging, and operational guardrails in multi-agent systems.