Job Description
AI Engineer - Agentic AI & Generative AI
Location : Chennai / Bengaluru
Experience : 2- 7 Years
Employment Type : Full-Time
Department : Data Science & Artificial Intelligence
About the Role :
We are seeking an innovative AI Engineer with expertise in Generative AI (GenAI) and Agentic AI to design, develop, and deploy next-generation AI-powered applications and autonomous intelligent systems. The ideal candidate will have hands-on experience building enterprise-grade AI solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, LangChain, and Multi-Agent Architectures. In this role, you will collaborate with cross-functional teams to develop scalable AI platforms, intelligent automation workflows, and production-ready AI applications that solve complex business problems across multiple domains.
Key Responsibilities :
1. AI Solution Architecture :
- Design scalable, secure, and cloud-native AI solution architectures aligned with business goals and enterprise technology standards.
- Evaluate business requirements and recommend appropriate AI models, frameworks, and deployment strategies.
- Define reusable AI architecture patterns and best practices for enterprise implementations.
- Collaborate with solution architects, product teams, and business stakeholders during solution design.
2. Agentic AI Development :
- Design and develop autonomous AI agents capable of reasoning, planning, decision-making, and executing complex multi-step tasks.
- Build multi-agent systems where specialized AI agents collaborate to accomplish business workflows.
- Develop intelligent orchestration frameworks for agent communication, task routing, memory management, and tool integration.
- Implement autonomous workflow automation using Agentic AI principles.
3. Generative AI & Large Language Models :
- Develop AI-powered applications using Large Language Models (LLMs).
- Integrate OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini, Llama, Mistral, or similar foundation models.
- Design prompt engineering strategies for high-quality, context-aware AI responses.
- Fine-tune, evaluate, and optimize foundation models for domain-specific use cases.
- Develop conversational AI assistants, enterprise copilots, document intelligence, and knowledge assistants.
4. Retrieval-Augmented Generation (RAG) :
- Design and implement enterprise RAG pipelines.
- Build ingestion frameworks for structured and unstructured enterprise documents.
- Develop semantic search solutions using vector databases.
- Implement document chunking, embedding generation, indexing, retrieval optimization, and response synthesis.
- Optimize retrieval quality and minimize hallucinations through advanced RAG techniques.
5. AI Application Development :
- Develop backend APIs and AI microservices supporting enterprise AI applications.
- Build interactive web-based AI applications and user interfaces.
- Integrate AI models with enterprise applications, APIs, databases, and third-party systems.
- Develop scalable AI services capable of handling high transaction volumes.
6. MLOps & AI Operations :
- Build CI/CD pipelines for AI model deployment.
- Automate model training, testing, deployment, and monitoring.
- Implement model versioning, experiment tracking, and reproducibility.
- Monitor model performance, latency, drift, and reliability in production.
- Support continuous model improvement through feedback loops.
7. Cloud & Platform Engineering :
- Deploy AI workloads on Microsoft Azure, AWS, or Google Cloud Platform.
- Develop containerized AI applications using Docker and Kubernetes.
- Build scalable AI infrastructure supporting enterprise production environments.
- Optimize infrastructure for performance, security, and cost.
8. AI Governance, Security & Responsible AI :
- Implement responsible AI practices including explainability, fairness, transparency, and bias detection.
- Ensure compliance with enterprise AI governance, security, privacy, and regulatory requirements.
- Protect sensitive enterprise data through secure AI architecture and access controls.
- Develop monitoring frameworks for AI safety and compliance.
9. Technical Leadership :
- Participate in solution architecture reviews and technical design discussions.
- Establish coding standards and AI engineering best practices.
- Conduct code reviews and mentor junior engineers.
- Evaluate emerging AI technologies and recommend adoption strategies.
- Drive innovation initiatives related to Agentic AI and enterprise Generative AI.
Required Skills & Experience :
The ideal candidate should have hands-on experience in designing and deploying enterprise AI solutions using modern Generative AI and Agentic AI technologies.
1. Artificial Intelligence & Machine Learning :
- Strong understanding of Generative AI, Large Language Models (LLMs), NLP, Machine Learning, Deep Learning, and AI application development.
- Experience building enterprise-grade AI assistants, copilots, and intelligent automation solutions.
2. Agentic AI :
- Hands-on experience developing AI Agents, autonomous workflows, multi-agent systems, and intelligent orchestration frameworks.
- Knowledge of agent planning, memory management, reasoning, and tool execution.
3. Generative AI Frameworks :
- Experience with LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, DSPy, or similar AI orchestration frameworks.
- Strong prompt engineering and LLM optimization skills.
- Experience integrating OpenAI, Azure OpenAI, Claude, Gemini, Llama, or other foundation models.
4. RAG & Vector Search :
- Experience building Retrieval-Augmented Generation (RAG) applications.
- Hands-on knowledge of embedding models, semantic search, vector databases, and document retrieval pipelines.
- Experience with Pinecone, Weaviate, Milvus, ChromaDB, FAISS, or Azure AI Search.
5. Programming :
- Strong proficiency in Python.
- Experience developing REST APIs using FastAPI or Flask.
- Knowledge of JavaScript or TypeScript is an added advantage.
6. Cloud Technologies :
- Experience deploying AI applications on Microsoft Azure, AWS, or Google Cloud Platform.
- Familiarity with Azure OpenAI, AWS Bedrock, Vertex AI, or equivalent AI services.
7. MLOps & DevOps :
- Experience with Git, Docker, Kubernetes, CI/CD pipelines, MLflow, LangSmith, and model monitoring tools.
- Knowledge of model deployment, observability, and production AI operations.
8. Databases :
- SQL and NoSQL databases.
- Vector databases.
- Enterprise data integration.
Preferred Qualifications :
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Engineering, or a related discipline.
- Relevant certifications in Azure AI Engineer, AWS Machine Learning, Google Professional Machine Learning Engineer, or Generative AI technologies will be an added advantage.