Senior GenAI / Agentic AI Engineer

InspironLabs; Mumbai; On-site; PHP 1,200,000 - 2,400,000; Full time

Job summary

InspironLabs is seeking a Senior GenAI Engineer in the Philippines to design, build and deploy production-grade GenAI and agentic AI solutions. You will architect multi-agent systems, optimize RAG pipelines, and ensure secure cloud deployments across enterprise platforms.

The role requires hands-on expertise with Python, FastAPI, LLMs, and modern agentic frameworks, plus experience with cloud providers and vector databases.

Qualifications

• Design and deploy production-grade GenAI solutions.
• Develop scalable AI pipelines and multi-agent systems.
• Implement RAG with retrieval, vector DBs, and context management.
• Evaluate performance with prompt engineering and HITL workflows.
• Secure cloud deployments and enterprise integrations.

Responsibilities

• Design, develop, and deploy GenAI solutions using LLMs.
• Build RAG pipelines with document processing and retrieval.
• Design multi-agent architectures with tools, memory, planning.
• Develop backend services and APIs using Python/FastAPI.
• Monitor and improve LLM performance; ensure secure cloud deployment.

Skills

LLM solutions

Agentic AI frameworks

Python

FastAPI

Async programming

RAG pipelines

Vector databases

Prompt engineering

Multi-agent architecture

Enterprise integrations

Cloud deployment

Secure credential management

Education

Bachelor’s/Master’s in CS/IT

Tools

LangGraph

LangChain

AutoGen

CrewAI

FAISS

Pinecone

pgvector

Job description

Experience: 6-12 Years

Are you an experienced GenAI/Agentic AI professional with a strong track record of building and deploying production-grade AI solutions? We’re looking for a Senior GenAI / Agentic AI Engineer with strong hands-on expertise in developing scalable, real-world AI solutions and a passion for building intelligent systems using the latest advancements in GenAI and Agentic AI.

Job 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 capabilities such as tool use, memory, planning, guardrails, and observability.
• Develop scalable backend services and APIs using Python, FastAPI, and asynchronous programming, while integrating AI solutions with enterprise platforms and systems.
• Evaluate, monitor, and improve LLM performance through prompt engineering, LLM evaluations, HITL workflows, and secure cloud-based deployment practices.

Required Skills-

• Production-grade LLM solutions – OpenAI, Anthropic, Azure OpenAI
• Agentic AI frameworks – LangGraph, LangChain, AutoGen, CrewAI
• Python, FastAPI & async programming
• RAG pipelines and vector databases – FAISS, Pinecone, pgvector
• Prompt engineering, LLM evaluations & HITL workflows
• Azure / AWS / GCP cloud deployment
• Multi-agent architecture – tool use, memory, planning, guardrails & observability
• Enterprise integrations – Graph API, Power Automate, Salesforce, etc.
• Secure credential management, managed identity & enterprise integration patterns.

Qualifications-

• Bachelor’s/ Master’ s in CS/IT or equivalent practical experience.
• We’re looking for professionals who have delivered real-world, production-grade GenAI/Agentic AI solutions — not just POCs.