Gen AI (Python) Engineer Job ID: 382097

Setoo; Pune District; On-site; INR 1,800,000 - 2,800,000; Full time

Job summary

Setoo is seeking a Generative AI Engineer to design and implement AI-driven solutions for document processing and decision support. The role focuses on building LLM-powered applications using Retrieval-Augmented Generation (RAG) to deliver explainable outputs from large datasets.

You will design, build, and deploy RAG-based AI solutions, develop retrieval pipelines, implement prompt engineering, and integrate LLMs into production systems.

Qualifications

• 3–5 years of experience in AI/ML, NLP, or applied ML roles.
• Strong proficiency in Python and ML frameworks (PyTorch, TensorFlow, Hugging Face).
• Hands-on experience with LLMs and Retrieval-Augmented Generation (RAG).
• Experience with vector databases and embeddings-based retrieval.
• Experience deploying AI models and services in cloud environments.
• Understanding of data security and governance principles.

Responsibilities

• Design, build, and deploy RAG-based AI solutions for document analysis and automation.
• Develop and optimize retrieval pipelines using embeddings and vector databases.
• Implement prompt engineering and context-aware generation workflows.
• Integrate LLM applications into production systems via APIs and microservices.
• Collaborate with data engineering to prepare structured and unstructured data for retrieval.
• Monitor model outputs for accuracy and reduce hallucinations.
• Monitor AI pipelines and continuously improve system performance.
• Ensure responsible AI usage, data privacy, and regulatory compliance.

Skills

Python

ML frameworks

LLMs

RAG architectures

Vector databases

Cloud deployment

Data security

Tools

FAISS

Pinecone

Weaviate

Chroma

Job description

Generative AI Engineer (3–5 Years Experience)

We are seeking a Generative AI Engineer to design and implement AI-driven solutions that automate document processing, decision support, and analytical workflows. The role will focus on building LLM-powered applications using Retrieval-Augmented Generation (RAG) to deliver accurate, explainable, and domain-aware outputs from large, complex datasets.

Key Responsibilities

• Design, build, and deployRAG-based AI solutionsusing large language models for document analysis, summarization, and intelligent automation.
• Develop and optimizeretrieval pipelinesleveraging embeddings and vector databases.
• Implement prompt engineering strategies and context-aware generation workflows.
• Integrate LLM applications into production systems via APIs and microservices.
• Collaborate with data engineering teams to prepare structured and unstructured data for retrieval and indexing.
• Evaluate model outputs for accuracy, relevance, and hallucination reduction.
• Monitor AI pipelines and continuously improve system performance.
• Ensure responsible AI usage, data privacy, and compliance with regulatory requirements.

Required Skills & Experience

• 3–5 years of experience in AI/ML, NLP, or applied machine learning roles.
• Strong proficiency in Python and ML frameworks (PyTorch, TensorFlow, Hugging Face).
• Hands-on experience withLLMs and RAG architectures.
• Experience withvector databases(e.g., FAISS, Pinecone, Weaviate, Chroma).
• Knowledge of embeddings, similarity search, and retrieval strategies.
• Experience deploying AI models and services in cloud environments.
• Solid understanding of data security and governance principles.

Nice to Have

• Experience working with healthcare, insurance, legal, or regulatory text data.
• Familiarity with document ingestion pipelines (PDFs, scanned docs, OCR).
• Exposure to model monitoring, evaluation frameworks, and guardrails.