We are seeking an experienced Senior Agentic AI / Automation Engineer to design, develop, and deploy next-generation AI-powered enterprise applications using Large Language Models (LLMs), Agentic AI frameworks, Retrieval-Augmented Generation (RAG), workflow orchestration, and intelligent automation technologies. This role is ideal for professionals passionate about building autonomous AI agents, enterprise AI platforms, cloud-native applications, and scalable automation solutions.
As a Senior Agentic AI / Automation Engineer, you will collaborate with software engineers, AI researchers, cloud architects, product managers, and enterprise stakeholders to build secure, production-grade AI systems. You will lead the development of AI-driven applications using modern foundation models, cloud platforms, vector databases, and enterprise APIs while ensuring scalability, governance, compliance, and operational excellence.
This opportunity provides hands-on exposure to Generative AI, Agentic AI, LLM Engineering, AI Workflow Automation, Cloud Infrastructure, Enterprise Integration, and AI Governance, enabling you to work on cutting-edge enterprise AI transformation initiatives.
Key Responsibilities
Agentic AI & Generative AI Development
- Design, develop, and deploy enterprise AI applications using Large Language Models (LLMs).
- Build autonomous AI agents capable of planning, reasoning, and executing multi-step workflows.
- Implement Agentic AI architectures using modern orchestration frameworks.
- Develop AI-powered automation solutions that integrate with enterprise applications.
- Build reusable AI services supporting enterprise-scale automation initiatives.
- Design AI workflows with human-in-the-loop decision-making capabilities.
LLM Engineering & AI Workflows
- Develop applications using OpenAI, Anthropic Claude, Google Gemini, or similar foundation models.
- Implement Prompt Engineering techniques to improve model accuracy and reliability.
- Design Retrieval-Augmented Generation (RAG) pipelines for enterprise knowledge systems.
- Build structured prompting and tool-calling workflows.
- Fine-tune AI models where appropriate to improve business outcomes.
- Optimize AI reasoning, response quality, and inference performance.
Enterprise AI Integration
- Integrate AI services with enterprise APIs, internal applications, and business platforms.
- Develop secure RESTful APIs supporting AI-powered applications.
- Connect AI systems with enterprise data pipelines and knowledge repositories.
- Build scalable backend services supporting AI inference and automation.
- Enable AI-driven business process automation across enterprise systems.
Cloud & Platform Engineering
- Deploy AI workloads on Google Cloud Platform (GCP), Microsoft Azure, or Kubernetes environments.
- Develop cloud-native AI applications using Docker and Kubernetes.
- Manage scalable AI infrastructure supporting enterprise workloads.
- Optimize cloud resource utilization and operational efficiency.
- Implement secure deployment strategies following enterprise cloud standards.
Vector Databases & Knowledge Retrieval
- Design enterprise Retrieval-Augmented Generation (RAG) architectures.
- Integrate vector databases such as Pinecone, Weaviate, Elasticsearch, or OpenSearch.
- Build semantic search and enterprise knowledge retrieval systems.
- Improve AI response quality using intelligent document retrieval strategies.
- Optimize indexing, embeddings, and retrieval performance.
AI Performance, Monitoring & Optimization
- Monitor AI application performance, latency, accuracy, and cost efficiency.
- Evaluate LLM outputs using automated evaluation frameworks.
- Implement AI observability and monitoring solutions.
- Optimize prompts, caching strategies, batching, and model selection.
- Detect model drift and continuously improve AI performance.
Security, Governance & Responsible AI
- Implement Responsible AI principles throughout the AI lifecycle.
- Ensure compliance with enterprise security, governance, and regulatory standards.
- Design secure AI applications with encryption, IAM, and access control.
- Support AI risk assessments and governance reviews.
- Maintain secure AI deployment pipelines for regulated enterprise environments.
Leadership & Collaboration
- Lead technical initiatives across enterprise AI engineering projects.
- Mentor engineers in AI engineering best practices and software development.
- Participate in architecture reviews and technical strategy discussions.
- Collaborate with product managers, architects, security teams, and business stakeholders.
- Stay updated with emerging AI technologies, frameworks, and industry best practices.
Required Skills
Artificial Intelligence
- Generative AI
- Agentic AI
- Large Language Models (LLMs)
- Prompt Engineering
- AI Workflow Orchestration
- Multi-Agent Systems
- AI Automation
- AI Reasoning
- Foundation Models
LLM Platforms
- OpenAI
- Anthropic Claude
- Google Gemini
- Azure OpenAI
- Google Vertex AI (Preferred)
Agent Frameworks
- LangChain
- LangGraph
- CrewAI
- AutoGen
- Semantic Kernel
- OpenAI Agents SDK
- Microsoft AutoGen
Programming
- Python
- REST API Development
- FastAPI
- Flask
- JSON
- Async Programming
Cloud Platforms
- Google Cloud Platform (GCP)
- Microsoft Azure
- Kubernetes
- Docker
- OpenShift
Vector Databases
- Pinecone
- Weaviate
- Elasticsearch
- OpenSearch
- ChromaDB
- FAISS
AI Engineering
- Retrieval-Augmented Generation (RAG)
- Fine-Tuning
- Structured Prompting
- Tool Calling
- Function Calling
- Embeddings
- Semantic Search
- Knowledge Retrieval
Software Engineering
- Git
- GitHub
- CI/CD Pipelines
- Software Architecture
- Microservices
- API Integration
- Enterprise Application Development
Security & Governance
- Identity & Access Management (IAM)
- Cloud Security
- AI Governance
- Responsible AI
- Compliance
- Data Security
- Enterprise Risk Management
Monitoring & Observability
- AI Evaluation Frameworks
- Latency Monitoring
- Cost Optimization
- Drift Detection
- Prompt Evaluation
- AI Observability
Professional Skills
- Technical Leadership
- Problem Solving
- Analytical Thinking
- Enterprise Architecture
- Cross-functional Collaboration
- Stakeholder Management
- Technical Documentation
- Mentoring & Coaching
- Innovation Mindset
- Communication Skills
Preferred Skills
- Power Platform
- Power Apps
- Dataverse
- UiPath
- Enterprise Automation
- AI-assisted Software Development
- Open Source AI Contributions
- Feature Stores
- Model Registries
- AI MLOps
- Enterprise Data Platforms
- Secure AI Pipelines
Education
Undergraduate
- Bachelor’s degree in Computer Science, Information Technology, Artificial Intelligence, Software Engineering, Data Science, or a related technical discipline.
- B.Tech / BE
- BCA (with relevant experience)
Postgraduate (Preferred)
- MCA
- M.Tech
- M.Sc. (Artificial Intelligence / Computer Science / Data Science)
- Master’s degree in AI, Machine Learning, or Software Engineering