Gen AI Developer

UsefulBI Corporation; Pune District; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

UsefulBI Corporation is seeking a Generative AI/Agentic AI Developer in Pune to design, develop, and deploy GenAI-powered applications. The role focuses on building AI agents, multi-agent workflows, and autonomous task execution systems within enterprise-scale deployments.

You will work with LLM ecosystems, prompt engineering, and AI orchestration to deliver scalable solutions, integrating diverse LLMs and vector databases. The position demands strong Python skills and cloud experience.

Qualifications

• Strong proficiency in Python.
• Hands-on experience with LLMs and Generative AI frameworks.
• Experience with LangChain, LangGraph, CrewAI, LlamaIndex, or similar frameworks.
• Strong understanding of RAG architecture and vector databases (Pinecone, ChromaDB, FAISS, Weaviate, etc.).
• Experience with prompt engineering and LLM optimization.
• Exposure to multi-agent systems and Agentic AI workflows.
• Knowledge of NLP, embeddings, semantic search, and AI orchestration.
• Experience with REST APIs, FastAPI, or backend integration.
• Exposure to cloud platforms such as AWS, Azure, or GCP.
• Understanding of CI/CD, Docker, and deployment workflows.

Responsibilities

• Design and develop GenAI and Agentic AI applications using LLMs.
• Build AI agents, multi-agent workflows, and autonomous task execution systems.
• Develop RAG-based pipelines using vector databases and retrieval frameworks.
• Integrate LLMs such as OpenAI, Claude, Gemini, Llama, or Mistral into enterprise applications.
• Work on prompt engineering, fine‑tuning, evaluation, and response optimization.
• Build AI‑powered assistants, Q&A systems, summarizers, automation bots, and intelligent workflows.
• Develop scalable APIs and backend services for AI applications.
• Collaborate with Data Engineering and Product teams for AI solution deployment.
• Optimize model performance, latency, and cost efficiency.

Skills

Python

LLMs

Prompt engineering

Multi-agent systems

NLP embeddings

REST APIs

FastAPI

Cloud platforms

CI/CD

Docker

AI orchestration

Tools

LangChain

LangGraph

CrewAI

LlamaIndex

Pinecone

ChromaDB

FAISS

Weaviate

Job description

We are looking for a Generative AI / Agentic AI Developer with strong experience in Large Language Models (LLMs), AI Agents, RAG architectures, and intelligent automation systems. The role involves designing, developing, and deploying next-generation AI-powered applications using modern GenAI frameworks and multi-agent architectures. The ideal candidate should have hands‑on experience with LLM ecosystems, prompt engineering, AI orchestration frameworks, vector databases, and cloud-based AI deployments. The candidate will work closely with Data Engineering, Product, and AI teams to build scalable AI‑driven solutions for enterprise use cases.

Key Responsibilities:

• Design and develop GenAI and Agentic AI applications using LLMs
• Build AI agents, multi-agent workflows, and autonomous task execution systems
• Develop RAG-based pipelines using vector databases and retrieval frameworks
• Integrate LLMs such as OpenAI, Claude, Gemini, Llama, or Mistral into enterprise applications
• Work on prompt engineering, fine‑tuning, evaluation, and response optimization
• Build AI‑powered assistants, Q&A systems, summarizers, automation bots, and intelligent workflows
• Develop scalable APIs and backend services for AI applications
• Collaborate with Data Engineering and Product teams for AI solution deployment
• Optimize model performance, latency, and cost efficiency

Required Skills:

• Strong proficiency in Python
• Hands‑on experience with LLMs and Generative AI frameworks
• Experience with LangChain, LangGraph, CrewAI, LlamaIndex, or similar frameworks
• Strong understanding of RAG architecture and vector databases (Pinecone, ChromaDB, FAISS, Weaviate, etc.)
• Experience with prompt engineering and LLM optimization
• Exposure to multi‑agent systems and Agentic AI workflows
• Knowledge of NLP, embeddings, semantic search, and AI orchestration
• Experience with REST APIs, FastAPI, or backend integration
• Exposure to cloud platforms such as AWS, Azure, or GCP
• Understanding of CI/CD, Docker, and deployment workflows