Agentic AI Engineer - Immediate Joiners only

Epitria Consulting; Hyderabad; On-site; INR 3,000,000 - 5,000,000; Full time

Job summary

Epitria Consulting seeks an AI Engineer to design and deploy Agentic AI systems leveraging LLMs, RAG architectures, and MCP-like protocols for scalable, production-grade solutions.

The role requires 5+ years in software or AI engineering, strong Python skills, and hands-on experience with LangChain, vector databases, Docker/Kubernetes. Hybrid work across Bengaluru/Hyderabad/Pune/Gurugram with cloud deployments on AWS/Azure/GCP.

Qualifications

• 5+ years of experience in software engineering or AI engineering roles.
• Strong proficiency in Python and modern backend frameworks (FastAPI, Flask, etc.).
• Hands-on experience with LLM frameworks such as LangChain, LlamaIndex, or similar.
• Strong understanding of RAG architectures, embeddings, chunking, and retrieval strategies.
• Experience with vector databases (Pinecone, Weaviate, FAISS, Chroma, etc.).
• Experience building agentic workflows (tool use, memory, planning, orchestration).
• Familiarity with MCP (Model Context Protocol) or similar tool-interaction paradigms.
• Experience deploying AI applications on cloud platforms (AWS/Azure/GCP).
• Strong knowledge of Docker, Kubernetes, and microservices architecture.
• Experience designing and consuming REST APIs / async systems.

Responsibilities

• Design and build Agentic AI systems capable of planning, reasoning, and tool usage.
• Develop and optimize RAG (Retrieval-Augmented Generation) pipelines for enterprise use cases.
• Implement and integrate Model Context Protocol (MCP) or similar frameworks for tool orchestration.
• Build multi-agent workflows and autonomous decision-making systems.
• Deploy AI applications on cloud platforms (AWS, Azure, GCP) with scalability and reliability.
• Develop APIs and services to integrate LLM-powered features into products.
• Work with vector databases and retrieval systems for efficient knowledge access.
• Optimize latency, cost, and performance of LLM-based applications.
• Implement observability, monitoring, and evaluation frameworks for AI systems.
• Collaborate with product and engineering teams to deliver production-grade AI solutions.

Skills

Python

FastAPI/Flask

LangChain

RAG pipelines

Vector databases

Docker

Kubernetes

MCP (Model Context Protocol)

Cloud platforms (AWS/Azure/GCP)

REST APIs

Multi-agent workflows

Tools

LangChain

LlamaIndex

Pinecone

Weaviate

Job description

We are looking for an AI Engineer specializing in Agentic AI systems and cloud-native deployment. This role focuses on building intelligent, autonomous systems using LLMs, RAG architectures, and emerging protocols like MCP, with an emphasis on scalable, production-ready implementations.

Experience: 5 years - Minimum 5 years of experience is required.

Location: Hybrid - Bengaluru/ Hyderabad/ Pune/ Gurugram

Shift Timings: 12 PM - 9 PM IST

**Looking for immediate joiners only**

Key Responsibilities

• Design and build Agentic AI systems capable of planning, reasoning, and tool usage
• Develop and optimize RAG (Retrieval-Augmented Generation) pipelines for enterprise use cases
• Implement and integrate Model Context Protocol (MCP) or similar frameworks for tool orchestration
• Build multi-agent workflows and autonomous decision-making systems
• Deploy AI applications on cloud platforms (AWS, Azure, GCP) with scalability and reliability
• Develop APIs and services to integrate LLM-powered features into products
• Work with vector databases and retrieval systems for efficient knowledge access
• Optimize latency, cost, and performance of LLM-based applications
• Implement observability, monitoring, and evaluation frameworks for AI systems
• Collaborate with product and engineering teams to deliver production-grade AI solutions

Required Skills & Qualifications

• 5+ years of experience in software engineering or AI engineering roles
• Strong proficiency in Python and modern backend frameworks (FastAPI, Flask, etc.)
• Hands‑on experience with LLM frameworks such as LangChain, LlamaIndex, or similar
• Strong understanding of RAG architectures, embeddings, chunking, and retrieval strategies
• Experience with vector databases (Pinecone, Weaviate, FAISS, Chroma, etc.)
• Experience building agentic workflows (tool use, memory, planning, orchestration)
• Familiarity with MCP (Model Context Protocol) or similar tool-interaction paradigms
• Experience deploying AI applications on cloud platforms (AWS/Azure/GCP)
• Strong knowledge of Docker, Kubernetes, and microservices architecture
• Experience designing and consuming REST APIs / async systems

Preferred Qualifications

• Experience with multi-agent systems and orchestration frameworks
• Familiarity with prompt engineering, evaluation, and guardrails
• Knowledge of LLM observability tools (LangSmith, Weights & Biases, etc.)
• Experience with streaming architectures and real-time AI systems
• Exposure to security and governance in AI systems
• Understanding of cost optimization strategies for LLM usage

Soft Skills

• Strong problem-solving and system design skills
• Ability to work in fast-evolving AI landscapes
• Good communication and cross-functional collaboration