Generative AI Engineer - Python

Description :
Job Description : Generative AI Engineer (Python, LLM, RAG) 34 Years | Mumbai

Location : Mumbai (Hybrid/On-site)

Experience : 34 Years

Role : Generative AI / LLM Engineer

Department : AI/ML / Data Science / Engineering

Employment Type : Full-Time

About the Role :

We are seeking a skilled Generative AI Engineer with strong expertise in Python, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). The ideal candidate will work on designing, developing, and deploying GenAI-driven solutions that enhance automation, analytics, and business intelligence.

Key Responsibilities :

1. LLM & GenAI Development :

- Develop, fine-tune, and customize LLMs for various business use cases.

- Build RAG pipelines, conversational agents, summarization systems, and content-generation tools.

- Perform prompt engineering, model evaluation, and continuous optimization.

2. Python Engineering :

- Develop scalable Python-based applications and microservices.

- Implement APIs (FastAPI/Flask) to integrate AI models into applications.

- Work with ETL pipelines, data processing flows, and automation scripts.

3. RAG Workflow & Vector Databases :

- Build RAG architectures using FAISS, Pinecone, ChromaDB, Weaviate, or similar tools.

- Handle embeddings generation, retrieval pipelines, and document processing.

- Implement chunking strategies, indexing, and retrieval performance improvements.

4. Data & Model Pipeline Management :

- Clean, preprocess, and manage large unstructured datasets (PDFs, text corpora, logs).

- Work with embeddings (OpenAI, Sentence Transformers, LLaMA embeddings, etc.).

- Utilize ML frameworks like PyTorch or TensorFlow.

5. Deployment & MLOps :

- Deploy models using Docker, Kubernetes, or cloud platforms (AWS/GCP/Azure).

- Implement CI/CD, monitoring, versioning, and lifecycle management.

- Optimize latency, scalability, and infrastructure costs.

Required Skills :

- Strong proficiency in Python

- Hands-on experience with LLMs (OpenAI, LLaMA, Mistral, Falcon, etc.)

- Strong experience in building RAG systems

- Proficiency with LangChain, LlamaIndex, or similar orchestration frameworks

- Experience with vector databases (FAISS, Pinecone, ChromaDB, Milvus)

- Solid understanding of embeddings, tokenization, and prompt engineering

- Experience with PyTorch or TensorFlow

- Strong command of REST API development

- Experience with Git, Docker, and cloud platforms

Good to Have :

- Experience fine-tuning open-source LLMs

- Knowledge of multimodal AI (image, text, speech models)

- Familiarity with MLflow, Databricks, or similar ML lifecycle tools

- Understanding of transformers architecture and NLP fundamentals

- Experience with PDF text extraction, OCR, and document processing

Qualifications :

- Bachelors or Masters degree in Computer Science, Data Science, AI/ML, Engineering, or related field.

Soft Skills :

- Strong analytical and problem-solving ability

- Excellent communication and collaboration skills

- Self-driven with the ability to work independently and in teams

- Attention to detail and ownership mindset