Agentic AI Engineer

About the Role

We are seeking an experienced AI Engineer with 4+ years of strong expertise in Generative AI and Agentic AI, combined with solid production engineering capabilities.

The ideal candidate will have hands-on experience building, deploying, and scaling LLM-powered systems — moving beyond prototypes into robust, enterprise-grade AI applications.

Key Responsibilities

• Design, build, and deploy GenAI / Agentic AI solutions, including:

o LLM pipelines

o Retrieval-Augmented Generation (RAG) systems

o Autonomous AI agents

• Develop scalable APIs, microservices, and model-serving architectures using cloud platforms (Azure preferred).

• Implement:

o Prompt engineering and prompt workflows

o Embeddings and vector search

o Guardrails and safety mechanisms for responsible AI

• Deploy production AI systems using:

o Docker, Kubernetes o CI/CD pipelines

o Monitoring and observability frameworks

• Integrate AI solutions with enterprise systems, data sources, and external APIs.

• Ensure reliability, performance, compliance, and alignment with Responsible AI standards.

Must-Have Skills (GenAI / Agentic AI)

• Hands-on experience in Generative AI development using models such as:

o GPT, Claude, Llama, Mistral, etc.

• Strong experience in Agentic AI, including:

o Multi-step AI agents o Tool-calling workflows

o Autonomous task pipelines

• Expertise in RAG architectures and vector databases such as:

o Pinecone, FAISS, Chroma, Azure Cognitive Search

• Proficiency in Python or JavaScript/TypeScript.

• Experience with frameworks like: o Azure OpenAI, LangChain, LlamaIndex, or similar

• Strong production engineering skills:

o Docker, Kubernetes

o CI/CD pipelines o API development and deployment best practices Nice to Have

• Model fine-tuning, quantization, or optimization experience.

• Familiarity with LLM evaluation frameworks such as:

o Ragas, TruLens, DeepEval

• Exposure to event-driven or real-time AI systems.

Job Location Chennai/Bangalore (Hybrid Model)