Senior Genai Agentic Ai Engineer Inspironlabs Bengaluru

Vibehackers; United States; On-site; USD 150,000 - 210,000; Full time

Job summary

Vibehackers is seeking a Senior GenAI / Agentic AI Engineer to design, develop, and deploy production-grade generative AI and agentic systems. You will build scalable RAG pipelines, multi-agent architectures, and backend APIs, integrating with enterprise platforms.

This role emphasizes secure, observable deployments on cloud platforms, using modern frameworks and HITL workflows to ensure reliable performance.

Qualifications

• Hands-on experience with LLMs and production deployments (OpenAI, Anthropic, Azure OpenAI).
• Experience with agentic AI frameworks such as LangGraph, LangChain, AutoGen, CrewAI.
• Strong Python development skills with FastAPI and asynchronous programming.
• Experience building RAG pipelines and using vector databases (FAISS, Pinecone, pgvector).
• Expertise in prompt engineering, LLM evaluations, and HITL workflows.
• Cloud deployment experience on Azure, AWS, and/or GCP with secure credential/managed identity patterns.
• Experience integrating with enterprise systems (Graph API, Power Automate, Salesforce).

Responsibilities

• Design, develop, and deploy production-grade GenAI and agentic AI solutions using LLMs and modern agentic frameworks.
• Build and optimize RAG pipelines, including document processing, retrieval strategies, vector databases, and context management.
• Design and implement multi-agent architectures with tool use, memory, planning, guardrails, and observability.
• Develop scalable backend services and APIs using Python, FastAPI, and asynchronous programming.
• Integrate AI solutions with enterprise platforms (e.g., Graph API, Power Automate, Salesforce) and manage secure credential patterns.
• Evaluate, monitor, and improve LLM performance through prompt engineering, LLM evaluations, and HITL workflows.
• Deploy and operate AI systems on cloud platforms with secure, managed-identity patterns and observability.

Skills

Prompt Engineering

LLM Evaluations

HITL workflows

Asynchronous Programming

API Development

Backend Development

Scalable System Design

RAG Pipelines

Vector Search

Multi-agent Architecture

Observability

Enterprise Integration

Cloud Deployment

Secure Credential Management

Education

Bachelor’s or Master’s degree in Computer Science/IT

Tools

LangGraph

LangChain

AutoGen

CrewAI

FAISS

Pinecone

pgvector

Job description

Building AI dev tools and multi-agent systems (agentic AI); focused on production-grade GenAI and integrations rather than frontend 'vibe coding'.

About the Role

Senior GenAI / Agentic AI Engineer responsible for designing, developing, and deploying production-grade generative AI and multi-agent solutions. The role focuses on building scalable RAG pipelines, multi-agent architectures, backend services/APIs, and integrating AI systems with enterprise platforms for secure, observable production deployments.

Job Description

Role

Senior GenAI / Agentic AI Engineer responsible for building and deploying production-grade generative AI and agentic systems. The engineer will design multi-agent architectures, RAG pipelines, and scalable backend services while integrating AI capabilities with enterprise systems and ensuring secure, observable deployments.

Key Responsibilities

• Design, develop, and deploy production-grade GenAI and agentic AI solutions using LLMs and modern agentic frameworks.
• Build and optimize RAG pipelines, including document processing, retrieval strategies, vector databases, and context management.
• Design and implement multi-agent architectures with tool use, memory, planning, guardrails, and observability.
• Develop scalable backend services and APIs using Python, FastAPI, and asynchronous programming.
• Integrate AI solutions with enterprise platforms (e.g., Graph API, Power Automate, Salesforce) and manage secure credential patterns.
• Evaluate, monitor, and improve LLM performance through prompt engineering, LLM evaluations, and HITL workflows.
• Deploy and operate AI systems on cloud platforms with secure, managed-identity patterns and observability.

Requirements

• Hands-on experience with LLMs and production deployments (OpenAI, Anthropic, Azure OpenAI).
• Experience with agentic AI frameworks such as LangGraph, LangChain, AutoGen, CrewAI.
• Strong Python development skills and experience with FastAPI and asynchronous programming.
• Experience building RAG pipelines and using vector databases (FAISS, Pinecone, pgvector).
• Expertise in prompt engineering, LLM evaluations, and HITL workflows.
• Cloud deployment experience on Azure, AWS, and/or GCP and knowledge of secure credential/managed identity patterns.
• Experience integrating with enterprise systems (Graph API, Power Automate, Salesforce).

Qualifications

• Bachelor’s or Master’s degree in Computer Science, IT, or equivalent practical experience.
• Experience level indicated: 6–12 years.
• Employment type: Contract or Full Time

Skills

Prompt Engineering LLM Evaluations HITL workflows Asynchronous Programming API Development Backend Development Scalable System Design Retrieval-Augmented Generation (RAG) Vector Search Multi-agent Architecture Observability Enterprise Integration Cloud Deployment Secure Credential Management