Software Engineer/Senior Software Engineer - Artificial Intelligence/Machine Learning

Role Summary :

We are seeking a highly skilled Generative AI & Conversational AI Expert to design, develop, and deploy cutting-edge AI solutions. This role will focus on both Conversational AI (chatbots, voice assistants, NLP, and dialogue frameworks) and Generative AI (LLMs, RAG, prompt engineering, and AI-based content generation).

The ideal candidate will have expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and modern NLP frameworks. You will be responsible for building AI-powered assistants, integrating AI into business workflows, and optimizing models for real-world applications.

Key Responsibilities :

Generative AI (Gen AI) :

- Develop AI-driven solutions using LLMs (e.g., GPT, LLaMA, Claude, Mistral) for business applications.

- Implement Retrieval-Augmented Generation (RAG) pipelines to provide AI with real-time business knowledge and context.

- Fine-tune and optimize LLMs for specific domains (e.g., Healthcare, Finance, Customer Support).

- Work with vector databases (e.g., Pinecone, FAISS, Weaviate, ChromaDB) to store and retrieve AI-relevant data.

- Develop knowledge graphs to enhance AI reasoning, memory, and structured data extraction.

- Conduct prompt engineering and tuning to improve the accuracy and relevance of AI-generated responses.

- Integrate LLM-based solutions into business automation workflows.

Conversational AI :

- Design and develop AI-powered chatbots and virtual assistants using platforms like Rasa, AWS Lex, Dialogflow, or OpenAI APIs.

- Implement speech-to-text (STT) and text-to-speech (TTS) for real-time voice AI interactions.

- Optimize dialogue management, NLU, and contextual understanding for seamless user experiences.

- Build multi-channel AI assistants (Web, WhatsApp, Slack, Microsoft Teams, IVR).

- Integrate Conversational AI solutions with backend systems, APIs, and databases for process automation.

- Deploy AI-driven customer service automation with human-agent handover capabilities.

Required Skills & Qualifications :

- Experience: 3-7 years of experience in AI/ML, NLP, or Conversational AI development.

- AI & NLP: Hands-on experience with LLMs, Transformer models, OpenAI APIs, Hugging Face, and LangChain.

- Frameworks: Proficiency with AI frameworks such as TensorFlow, PyTorch, Rasa, AWS Lex, or Dialogflow.

- Vector Databases & RAG: Knowledge of Pinecone, FAISS, Weaviate, or ChromaDB for AI memory storage.

- Conversational AI: Strong experience building intelligent chatbots and voice assistants.

- Voice/Speech: Understanding of STT, TTS, and multi-modal AI interactions.

- Model Optimization: Hands-on experience with LLM training, prompt tuning, and hyperparameter tuning.

- Integration: Experience integrating AI into enterprise applications, RPA tools, and cloud services.

- Cloud & Deployment: Experience with cloud platforms (AWS, Azure, GCP) and containerization (Docker, Kubernetes).

- Data Processing: Ability to structure data for AI reasoning and integrate with knowledge graphs.

- Programming: Proficiency in Python, Node.js, or Java.

- Soft Skills: Strong problem-solving, analytical skills, and a willingness to learn new technologies.

Preferred Qualifications :

- Experience with agentic AI architectures for task orchestration.

- Familiarity with AIOps, AI-driven decision-making, and automation strategies.

- Background in domains such as Healthcare AI, Financial AI, Enterprise AI, or Contact Center AI.

- Experience with process automation and structured data extraction.

(ref:hirist.tech)