Generative AI Engineer

Senior AI / GenAI Engineer

Job Title

Senior AI / GenAI Engineer

Experience

5–12 Years

Job Type

Full-time

Role Overview

We are looking for an experienced AI / GenAI Engineer with 5–12 years of hands-on experience in designing, developing, and deploying enterprise-grade AI and machine learning solutions.

The ideal candidate will have strong expertise in AI, Machine Learning, Generative AI, LLMs, Agentic AI, Chatbots, RAG, Python, and Azure Databricks . The candidate should be capable of taking AI solutions from ideation and experimentation through production deployment, optimization, and ongoing monitoring.

The role requires a strong combination of AI engineering, software development, data engineering, LLM application development, and cloud technologies , with the ability to work on scalable enterprise AI solutions.

Primary Skills

• Artificial Intelligence (AI)
• Machine Learning (ML)
• Generative AI (GenAI)
• Large Language Models (LLMs)
• Agentic AI / AI Agents
• Retrieval-Augmented Generation (RAG)
• AI-powered Chatbots
• Python
• Azure Databricks

Key Responsibilities

AI & Machine Learning

• Design, develop, train, evaluate, and deploy machine learning models.
• Apply appropriate ML algorithms to solve complex business problems.
• Perform data preparation, feature engineering, model development, validation, and optimization.
• Build scalable AI/ML solutions for enterprise use cases.
• Evaluate model performance and continuously improve accuracy, scalability, and reliability.

Generative AI & LLM

• Design and implement Generative AI applications using LLMs.
• Work with commercial and open-source LLMs and integrate them into enterprise applications.
• Develop LLM-based solutions for text generation, summarization, classification, information extraction, question answering, and conversational AI.
• Implement prompt engineering and optimize prompts for accuracy, relevance, and consistency.
• Work with embeddings, tokenization, context management, model evaluation, and LLM observability.
• Evaluate different LLM models based on quality, latency, cost, security, and business requirements.

Agentic AI

• Design and develop Agentic AI systems and autonomous AI agents .
• Build multi-step AI workflows capable of reasoning, planning, tool usage, and task execution.
• Develop AI agents that interact with APIs, databases, enterprise systems, and external tools.
• Implement agent orchestration, memory, context management, guardrails, and human-in-the-loop workflows.
• Design reliable and scalable agentic architectures for enterprise use cases.

RAG & Knowledge-Based AI

• Design and implement Retrieval-Augmented Generation (RAG) solutions.
• Build document ingestion, chunking, embedding, indexing, retrieval, and generation pipelines.
• Implement semantic search, hybrid search, metadata filtering, and contextual retrieval.
• Work with vector databases and enterprise knowledge repositories.
• Improve RAG accuracy through retrieval optimization, reranking, prompt engineering, and evaluation.
• Implement mechanisms to reduce hallucinations and improve response relevance and grounding.

AI Chatbots

• Develop intelligent AI-powered chatbots and conversational applications .
• Build context-aware, multi-turn conversational experiences.
• Integrate LLMs, RAG, APIs, enterprise data, and business workflows into chatbots.
• Implement conversation history, user context, authentication, guardrails, and fallback mechanisms.
• Monitor chatbot quality, response accuracy, latency, and user experience.

Python & Software Engineering

• Develop production-quality AI/ML applications using Python .
• Build reusable, modular, scalable, and testable AI components.
• Develop REST APIs and integrate AI services with enterprise applications.
• Follow software engineering best practices including Git, testing, CI/CD, code reviews, logging, and documentation.
• Optimize applications for performance, scalability, reliability, and cost.

Azure Databricks

• Design and develop AI/ML and data processing solutions using Azure Databricks .
• Work with Databricks notebooks, clusters, Spark, Delta Lake, and data pipelines.
• Process and transform large-scale datasets for AI/ML workloads.
• Develop ML workflows and integrate Databricks with Azure services.
• Support model development, experimentation, deployment, and monitoring.
• Optimize Spark/Databricks workloads for perform…