Junior Conversational AI And Agentic Workflow Developer

What role will you play in the team

As a Junior Conversational AI and Agentic Workflow Developer, you will be instrumental in designing autonomous AI agents, building sophisticated multi-step conversational flows, and integrating cutting-edge language models into mission-critical business applications. Your role focuses on bridging the gap between raw machine learning endpoints and functional enterprise utilities, utilizing workflow automation platforms, vector stores, and custom Python backend scripts to deliver intelligent, responsive, and reliable automated systems.

What you will do

You will build, test, and maintain complex conversational interfaces and autonomous agents using OpenAI API, Claude API, and advanced orchestration frameworks like n8n and Flowise. Your responsibilities include developing robust ETL pipelines to clean and embed unstructured enterprise documents, implementing Retrieval-Augmented Generation (RAG) frameworks to reduce hallucinations, and configuring secure webhooks to connect AI models with CRM and database systems. You will also participate in prompt engineering iterations, performance benchmarking, and troubleshooting deployment issues across cloud environments.

Key responsibility

• Engineer, test, and deploy intelligent conversational bots and AI agent workflows using advanced prompt engineering and orchestration tools.
• Integrate large language model endpoints such as OpenAI API and Claude API into scalable backend architectures using Python.
• Implement Retrieval-Augmented Generation (RAG) paradigms using vector databases and text embedding models for precise information retrieval.
• Construct automated end-to-end data integration pipelines and webhook triggers using n8n, Flowise, and Zapier Automation platforms.
• Process and clean large-scale unstructured textual datasets using modern ETL tools and Python-based data manipulation libraries.
• Monitor autonomous agent execution logs, analyze latency bottlenecks, and iteratively refine system architectures for optimal performance.
• Partner with product and engineering teams to translate business requirements into functional, scalable generative AI specifications.

Required Qualification and Skills

• Bachelor's degree in Information Technology, Data Analytics, Computer Science, or equivalent technical field with 0-1 years of experience.
• Demonstrated proficiency in Python programming and working with RESTful APIs and webhooks.
• Hands-on experience with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and prompt engineering best practices.
• Familiarity with workflow automation and low-code orchestration tools such as n8n, Flowise, and Zapier Automation.
• Basic understanding of database management systems including SQL, MongoDB, or PostgreSQL.
• Strong commitment to writing clean, maintainable code accompanied by comprehensive technical documentation.
• Exceptional problem-solving capabilities, adaptability, and eagerness to master emerging generative AI technologies.

Looking to get Placed? Try our Placement Guarantee Plan

Get Hired

Benefits Included

• Attractive annual compensation package aligned with leading market standards and regular performance reviews.
• Comprehensive health, dental, and life insurance benefits for employees and their immediate families.
• State-of-the-art office workspace located in a prime metropolitan hub with modern amenities.
• Ample opportunities for professional advancement through sponsored training programs and AI workshops.
• Encouraging hybrid work flexibility options and mental health support programs.
• Generous vacation policies, festive allowances, and annual team excursions.

A Day in the Life

Your morning kicks off with a daily stand-up where you report on the status of your latest AI agent deployment and review webhook error logs. Afterward, you dive into writing Python code to integrate a new Claude API endpoint into an existing data pipeline. In the afternoon, you build an automated workflow in n8n to ingest customer feedback files, generate vector embeddings, and store them in a PostgreSQL database. You spend your final hour testing prompt variations to improve the context-retrieval accuracy of a client support assistant.