About the Prospect

A fast-scaling AI-native tech firm specializing in enterprise-grade Generative AI and Agentic Systems, we build intelligent, self-orchestrating LLM applications that automate complex workflows—from customer service to internal knowledge retrieval. Our clients span fintech, healthcare, and SaaS, and we’re on a mission to turn RAG architectures and multi-agent frameworks into production-ready, high-impact solutions.

Role & Responsibilities

- Design, develop, and deploy RAG-enhanced LLM applications using LangChain, LlamaIndex, and Retrieval-Augmented Generation frameworks.
- Build agentic AI systems that autonomously reason, plan, and execute multi-step workflows using tool-calling, memory, and self-correction mechanisms.
- Integrate vector databases (Pinecone, Weaviate, FAISS) with LLMs for high-accuracy semantic search and context-aware responses.
- Optimize LLM inference pipelines for latency, throughput,



and cost—leveraging Azure/AWS/GCP and open-source inference servers like vLLM or TGI.
- Collaborate with product and data teams to define prompt engineering standards, hallucination mitigation, and evaluation metrics for agent performance.
- Ship end-to-end AI features in production: from data ingestion ➜ pipeline orchestration ➜ monitoring and A/B testing of agent behavior.

Skills & Qualifications

Must-Have

- LangChain
- LlamaIndex
- OpenAI API
- Anthropic Claude
- FAISS
- Pinecone
- Vector Databases
- Retrieval-Augmented Generation (RAG)

Preferred

- AutoGen
- Microsoft AutoGen Framework
- Agentic AI Architectures

Benefits & Culture Highlights

- 100% remote-first with flexible hours—focus on output, not office time.
- Annual upskilling budget for AI certifications and conferences.
- Work directly with clients across global industries—build solutions that matter.

📌 Gen AI/ Agentic AI Eng -Rag & LLM Application (5 yrs) (India)
🏢 Orbion Infotech
📍 India