Agentic AI Engineer

About the position

We are seeking an innovative and hands-on Agentic AI Engineer to design, build, and deploy autonomous AI agents that solve real business problems. You will develop intelligent AI systems capable of planning, reasoning, collaborating with other agents, integrating with enterprise applications, and executing complex workflows with minimal human intervention.

The ideal candidate has strong software engineering skills, experience with Large Language Models (LLMs), and a passion for building next-generation AI applications.

Location:

Gurugram

Roles & Responsibilities

• Build and maintain agentic workflows using frameworks like LangGraph(preferable),LangChain, CrewAI, AutoGen, N8N
• Implement tool/function calling integrations connecting agents to internal APIs, databases, and third-party services (including MCP-based connectors)
• Develop multi-step reasoning loops (ReAct, planner-executor, reflection patterns) and debug failure cases when agents go off-script
• Own prompt engineering and iteration for agent instructions, system prompts, and few-shot examples
• Implement short-term and long-term memory (vector stores, session state) so agents retain useful context
• Add guardrails: input/output validation, action confirmation steps, retry/rollback logic rate limiting on autonomous actions
• Set up observability — logging, tracing (LangSmith/Langfuse), and dashboards to monitor agent behavior in production
• Write evaluation harnesses (test cases, golden datasets, LLM-as-judge scoring) to catch regressions before deploy
• Work closely with senior engineers/leads on architecture decisions, and with product on translating workflows into agent capabilities
• Participate in code review, on-call rotation, and incident response for agent-related issues
• Stay current with emerging AI frameworks, models, and industry best practices.

ContinuumGlobal offers competitive salaries and benefits, including health insurance, and a flexible work environment. We are an equal opportunity employer, committed to a diverse and inclusive work environment. We strive to provide everyone with professional fulfilment and growth opportunities.

Job Specifications & Qualifications

• 5–7 years of professional software engineering experience, with 4+ years specifically working with LLMs/GenAI in production
• Strong Python (or TypeScript) skills; comfortable owning a service end-to-end
• Practical, hands-on experience with at least one agent orchestration framework (LangGraph, CrewAI, N8N, LlamaIndex, etc.) — not just tutorials, real shipped work
• Solid grasp of prompt engineering, function/tool calling, and structured output (JSON schema, Pydantic validation)
• Experience with RAG pipelines and vector databases (Pinecone, Weaviate, Chroma, pgvector)
• Understanding of LLM API usage patterns — streaming, retries, rate limits, cost/token management
• Familiarity with evaluating non-deterministic systems (eval sets, LLM-as-judge, A/B testing)
• Experience with REST/GraphQL APIs, Git, CI/CD, and basic cloud deployment (GCP)
• Ability to debug multi-step, non-deterministic pipelines without losing patience