Conversational AI Engineer/Consultant - Python/Chatbot (2-6 yrs)

Become a part of the ISPG Team :

ISPG does more than enhance the digital journey. It is a place to explore potential, transcend boundaries, and push out the edges of what can be. The company looks for people who can grow, think and develop.

About the Role :

Join our team and be part of a dynamic environment where innovation meets real-world AI applications. As a Conversational AI Engineer, you will design and develop cutting-edge AI solutions, working with LLMs, RAG, multi-modal AI, and knowledge-driven systems to create intelligent conversational experiences.

Required Experience Level : 2-5 Years

Job Location : Infopark, Cochin.

Technical Skills :

- High proficiency in Python programming, with experience in building AI-driven applications.

- Strong expertise in Cypher query writing for working with Neo4j graph databases.

- Knowledge of Retrieval-Augmented Generation (RAG) and Vector Search.

- Experience with LangChain, LangGraph, Hugging Face Transformers, OpenAI API.

- Understanding of multi-modal AI (text, image, audio, and video generation).

- Experience working with RAG and LLM-based applications for dialog and Q&A systems.

- Exposure to LLM function calling, information retrieval, vector databases, embedding models, rerank models, and autonomous agents.

- Hands-on experience in customising LangGraph framework and implementing multi-agent systems.

- Experience with GraphRAG for contextual awareness in chatbot responses.

- Experience in handling different LLM models, managing context size, and addressing token limit exceeding.

- Proficiency in React.js for building frontend applications and integrating LangGraph framework.

- Understanding of Graphiti for fact passing in knowledge-driven systems.

- Experience in in-memory caching customization with PostgreSQL for production-level performance.

- Experience deploying Kubernetes pods, Docker registry, and managing EC2 instances.

- Familiarity with Bitbucket pipelines, CI/CD automation, and scalable deployment strategies.

- Hands-on experience in handling latency issues, mitigating hallucinations, and optimizing AI workflows.

- Experience in passing API payloads in JSON format for frontend rendering as interactive cards.

- Expertise in session-based memory management (short-term and long-term) using MongoDB.

- Background in machine learning for product recommendation and personalization.

- Knowledge of Text-to-Speech (TTS) and Voice-to-Text (ASR) technologies, including:

- Amazon Polly, Amazon Transcribe, OpenAI Whisper for speech processing.

- Infusing TTS & voice functionalities into AI-driven chatbots.

- Experience with LLMs and Embedding Models, including:

- Groq, LLaMA, OpenAI (ChatGPT-4o, ChatGPT-4o Mini), Anthropic Claude.

- Text-Ada, Hugging Face Embedding Models, and other fine-tuned embedding models for vector search.

Responsibilities :

- Develop AI-powered applications for text generation, voice synthesis, and multimodal tasks.

- Build and optimize LLM-based APIs and services for production-ready AI solutions.

- Implement multi-turn, multi-user, multi-modal conversations using LangGraph and LLM agents.

- Analyze RAG and conversational AI agent performance, identify limitations, and improve accuracy.

- Customize and integrate conversational AI frameworks into scalable architectures.

- Address latency issues and hallucination handling in AI-generated responses.

- Frame system architecture for chatbot workflows with long-term and short-term memory mechanisms.

- Optimize in-memory caching using PostgreSQL for high-performance conversational AI.

- Design and deploy Kubernetes-based microservices for AI and chatbot applications.

- Work with GraphRAG and Graphiti to enable knowledge-driven AI responses.

- Connect backend AI services with React.js for smooth frontend interactions.

- Handle token limit exceeding, manage context size, and optimize API calls for cost efficiency.

- Develop ML-based product recommendation engines for personalized user experiences.

- Implement text-to-speech (TTS) and voice-to-text (ASR) functionalities using Amazon Polly, Whisper, and Transcribe.

- Ensure secure, scalable deployments using CI/CD pipelines (Bitbucket, Docker, Kubernetes).

- Write optimized Cypher queries for querying and managing Neo4j graph databases.

What We Offer :

- A collaborative and inclusive work environment.

- Opportunities for professional growth and development.

- Competitive salary and benefits package.

- The chance to work with a forward-thinking company at the forefront of the automotive industry.

If you're passionate about pushing the boundaries of conversational AI and optimizing AI performance, we would love to hear from you.