Generative AI Engineer

BizBrolly; Pune District, Dadri; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

Bizbrolly in Pune District is looking for a Senior Gen AI Engineer to design and scale production-ready AI systems. The ideal candidate will architect custom LLM workflows, fine-tune models, and optimize performance for enterprise-grade RAG pipelines.

Responsibilities include deploying advanced RAG systems, building autonomous agents, and implementing techniques to enhance model safety and accuracy.

Qualifications

• Expert in Python for AI-related development.
• Experience with PyTorch/TensorFlow.
• Familiarity with Hugging Face libraries.

Responsibilities

• Design and deploy advanced RAG systems using vector databases.
• Fine-tune open-source models using LoRA/QLoRA and PEFT.
• Build autonomous agents using LangChain, LangGraph, or LlamaIndex.
• Implement quantization and performance tuning to reduce latency.
• Build frameworks to ensure model safety and accuracy.

Skills

Expert Python

PyTorch/TensorFlow

Hugging Face

AWS Bedrock

Azure AI

Vertex AI

Vector embeddings

Prompt engineering

Semantic search

Job description

Role Summary

We are looking for a Senior Gen AI Engineer to design and scale production-ready AI systems. You will move beyond simple API prompts to architect custom LLM workflows, fine-tune models, and optimize enterprise-grade RAG pipelines.

Key Responsibilities

• LLM Architecting: Design and deploy advanced RAG systems using vector databases (Pinecone, Weaviate)
• Model Engineering: Fine-tune open-source models (Llama, Mistral) using LoRA/QLoRA and PEFT
• Agentic Workflows: Build autonomous agents using LangChain, LangGraph, or LlamaIndex
• Optimization: Implement quantization and performance tuning to reduce latency/cost
• Evaluation: Build frameworks to mitigate hallucinations and ensure model safety/accuracy.

Required Skills

• Core: Expert Python, PyTorch/TensorFlow, and Hugging Face
• Infrastructure: Proficiency in AWS Bedrock, Azure AI, or Vertex AI
• Data: Expertise in vector embeddings, prompt engineering, and semantic search.