About the Role :

We are looking for a highly skilled AI/ML Engineer Agentic AI to design, build, and deploy enterprise-grade autonomous AI systems powered by Large Language Models (LLMs).

This role requires expertise in developing intelligent AI agents capable of reasoning, planning, tool execution, memory management, and autonomous decision-making.

The ideal candidate will have strong hands-on experience with Python, Agentic AI frameworks, Retrieval-Augmented Generation (RAG), cloud platforms, and production-scale AI deployments.

Key Responsibilities :

- Design, develop, and deploy enterprise-grade autonomous AI agents.

- Build intelligent workflows capable of multi-step reasoning, planning, and task orchestration.

- Develop scalable AI applications using Python and modern Agentic AI frameworks.

- Design and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models.

- Integrate AI agents with enterprise applications, APIs, databases, and third-party SaaS platforms.

- Build conversational memory architectures, including both short-term and long-term memory.

- Implement planning, reasoning, feedback loops, and self-correction mechanisms.

- Develop secure tool-calling capabilities with validation, retries, timeout handling, and guardrails.

- Deploy AI applications using Docker, Kubernetes, and cloud-native services.

- Monitor production AI systems through logging, tracing, prompt management, and observability.

- Build evaluation frameworks to measure task success, latency, cost optimization, safety, and hallucination rates.

- Ensure Responsible AI practices, including data privacy, explainability, and human-in-the-loop workflows.

- Collaborate with cross-functional teams to deliver scalable enterprise AI solutions.

Required Technical Skills :

1. Programming & Backend Development :

- Expert-level proficiency in Python.

- Strong understanding of asynchronous programming, concurrency, and task scheduling.

- Experience developing scalable backend services and RESTful APIs.

2. Agentic AI :

- Design and development of autonomous AI agents.

- Multi-step reasoning and planning.

- Goal decomposition and workflow orchestration.

- Dynamic decision-making under uncertainty.

- Experience with ReAct, Plan-and-Execute, and Reflexive Agent architectures.

- Multi-agent and hierarchical agent systems.

- Tool calling and function execution.

- Stateful and stateless agent design.

3. Large Language Models (LLMs) :

- Hands-on experience with OpenAI, Azure OpenAI, Anthropic, or open-source LLMs.

- Prompt engineering and optimization.

- Chain-of-Thought, Few-shot, and Zero-shot prompting.

- Self-reflection and reasoning techniques.

- Model selection based on latency, context window, and cost.

- Experience with LoRA or model fine-tuning is an added advantage.

4. Agent Frameworks :

- LangChain

- LangGraph

- Semantic Kernel

- AutoGen

- CrewAI

- Custom orchestration frameworks

5. Retrieval-Augmented Generation (RAG) :

- Experience building enterprise RAG pipelines.

- Vector databases such as FAISS, Pinecone, and Azure AI Search.

- Embedding models and retrieval strategies.

- Chunking techniques and context compression.

- Knowledge Graph integration (preferred).

6. Planning & Control Systems :

- Task planning and re-planning.

- Constraint-based execution.

- Feedback loops.

- Guardrails.

- Action validation.

- Failure recovery strategies.

7. MLOps & AgentOps :

- Production deployment of AI agents.

- Prompt and model versioning.

- Agent tracing and observability.

- Logging and monitoring.

- CI/CD pipelines.

- Docker and Kubernetes.

- Azure/AWS serverless deployments.

8. Evaluation & Testing :

- Agent performance evaluation.

- Task success measurement.

- Cost and latency optimization.

- Hallucination detection.

- Offline testing frameworks.

- Simulation environments.

- Prompt and agent strategy A/B testing.

9. Security & Responsible AI :

- Prompt injection prevention.

- Jailbreak mitigation.

- Secure tool execution.

- Identity and privilege management.

- Data privacy and governance.

- Responsible AI implementation.

- Explainable AI (XAI).

- Human-in-the-loop workflows.

10. Data & Integration :

- REST APIs.

- Enterprise integrations (CRM, ERP, and business applications).

- SQL and NoSQL databases.

- Event-driven architectures.

- Message queues (preferred).

11. Cloud Platforms :

- Microsoft Azure (Preferred)

- Amazon Web Services (AWS)

- Google Cloud Platform (GCP)

- Managed AI services.

- Identity & Access Management (IAM).

- Secrets management.

- Cloud cost optimization.

Required Experience :

- 68 years of experience in Software Engineering, AI/ML Engineering, or related domains.

- Proven experience building and deploying production-grade AI applications.

- Strong expertise in developing enterprise Agentic AI solutions.

- Hands-on experience with LLMs, RAG pipelines, and AI orchestration frameworks.

- Experience deploying scalable AI solutions on Azure, AWS, or GCP.

Preferred Qualifications :

- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related field.

- Experience working in Agile/Scrum environments.

- Strong analytical, problem-solving, and communication skills.

Must-Have Skills :

- Python

- Agentic AI (LangGraph, LangChain, CrewAI, AutoGen)

- Large Language Models (OpenAI, Azure OpenAI, Anthropic)

- Retrieval-Augmented Generation (RAG) and Vector Databases

- Azure/AWS/GCP with Docker and Kubernetes

Good-to-Have Skills :

- Semantic Kernel

- Reinforcement Learning (RL)

- Knowledge Graphs

- LoRA Fine-tuning

- Enterprise Copilot Development

- Multi-Agent Systems

- AI Supervisor Architectures

- Human-AI Collaboration Workflows