Agentic AI Engineer

About the Role

We are seeking an Agentic AI Engineer to design, build, and deploy autonomous and

semi-autonomous AI agents capable of reasoning, planning, and executing complex tasks

with minimal human intervention.

In this role, you will work at the intersection of large language models (LLMs), multi-agent

systems, and real-world workflows, building intelligent agents that can interact with tools,

APIs, databases, and enterprise systems safely and reliably.

This is a hands-on engineering role with ownership across architecture, implementation,

evaluation, and deployment of agentic AI systems in production environments.

Key Responsibilities

Agent Design & Development

• Design and develop autonomous and semi-autonomous AI agents using state-of-the-art LLMs.
• Implement agent capabilities including reasoning, planning, memory, decision-making, and tool use.
• Build multi-agent systems where agents collaborate, coordinate, and delegate tasks to solve complex problems.

System Integration & Tooling

• Integrate AI agents with APIs, databases, internal services, and external tools.
• Design and implement agent workflows, tool-calling logic, and execution pipelines.
• Build RAG (Retrieval-Augmented Generation) pipelines using vector databases for knowledge-grounded reasoning.

Reliability, Safety & Evaluation

• Implement guardrails, validation layers, and human-in-the-loop mechanisms for safe execution.
• Design evaluation frameworks to measure agent performance, reliability, and task success.
• Monitor and mitigate issues such as hallucinations, tool misuse, and unintended actions.

Collaboration & Deployment

• Collaborate closely with product, backend, and ML teams to productionise AI solutions.
• Deploy and scale agent systems using cloud infrastructure, Docker, and CI/CD pipelines.
• Stay current with emerging agentic AI frameworks, research, and best practices.

Required Qualifications

• Strong experience with Python (or a similar backend language).
• Hands-on experience working with LLMs (OpenAI, Anthropic, Gemini, etc.).
• Practical knowledge of agentic AI frameworks such as LangChain, LangGraph, AutoGen, CrewAI
• Solid understanding of Agent reasoning and planning, Memory and state management, Tool usage and execution control
• Experience integrating AI systems with REST APIs, databases, and cloud services.
• Familiarity with prompt engineering, prompt evaluation, and agent debugging.
• Understanding of AI safety, monitoring, and hallucination mitigation techniques.
• Experience building production-grade AI agents deployed to real users.
• Background in machine learning, NLP, or applied AI research.
• Knowledge of multi-agent coordination, orchestration, and delegation patterns.
• Familiarity with vector databases such as FAISS, Pinecone, or Weaviate.

About Techtinium

Techtinium was started in Chennai in 2008. We are extremely passionate about solving real world technology problems. We always build something that is beyond expectation and that's why we have formed so many lasting relationships. We are a small and strong team of energetic individuals who are extremely agile and believe great experiences are made by small, flexible teams through an iterative process.