Machine Learning RAG Engineer

Grazitti Interactive; Mohali, Chandigarh, Panchkula; On-site; INR 900,000 - 1,500,000; Full time

Job summary

Grazitti Interactive seeks a Machine Learning Engineer to build next-generation search, retrieval, ranking, and RAG systems powering intelligent AI experiences at scale. You will work at the intersection of ML, Information Retrieval, NLP, and Generative AI, designing retrieval strategies, ranking models, evaluation frameworks, and production deployments from first principles.

This hand-on role spans experimentation, model development, evaluation, and deployment, with close collaboration with

Qualifications

• Strong foundation in ML, NLP, information retrieval and search relevance.
• Experience with Python and ML frameworks (PyTorch or TensorFlow).
• Hands-on with embeddings, vector search, BM25, ranking and reranking.
• Experience designing production ML systems from research to deployment.

Responsibilities

• Build and optimize search retrieval, ranking, and learning-to-rank models.
• Develop query understanding, intent classification, rewriting and expansion.
• Design semantic and hybrid retrieval using BM25, embeddings, vector search.
• Build and optimize RAG pipelines from document processing to grounded generation.
• Fine-tune embedding, reranking, and transformer-based models.
• Develop evaluation frameworks and datasets using metrics like NDCG, MRR, Recall@K.
• Collaborate with search and software engineers to optimize OpenSearch/Elasticsearch.
• Take ML solutions from prototype to production with focus on latency and reliability.

Skills

ML & NLP fundamentals

Python programming

PyTorch or TensorFlow

Hugging Face Transformers

Embeddings & vector search

OpenSearch/Elasticsearch

Production ML systems

Education

Bachelor's or Master's in CS/AI/Data Science

Tools

PyTorch

TensorFlow

Hugging Face Transformers

Sentence Transformers

Scikit-Learn

OpenSearch/Elasticsearch

Job description

Machine Learning Engineer Search, Retrieval & RAG

About the Role

We are looking for a Machine Learning Engineer to build next-generation Search, Retrieval, Ranking, and RAG systems that power intelligent AI experiences at scale.

This is not a "configure and optimize" role. You'll build the RAG and relevance intelligence from the ground up - designing retrieval strategies, ranking models, evaluation frameworks, and AI experiences from first principles. It's an opportunity to solve hard ML problems, experiment at scale, and leave your mark on the core platform.

You will work at the intersection of Machine Learning, Information Retrieval, NLP, and Generative AI, developing models and systems that understand user queries, retrieve the most relevant information, rank results effectively, and generate accurate, grounded responses.

This is a hands-on, end-to-end ML role spanning experimentation, model development, evaluation, and production deployment.

What You Will Do

• Build and optimize search retrieval, ranking, and Learning-to-Rank (LTR) models.
• Develop query understanding, intent classification, query rewriting, and query expansion solutions.
• Design semantic and hybrid retrieval using BM25, embeddings, and vector search.
• Build and optimize RAG pipelines covering document processing, chunking, embeddings, retrieval, reranking, and grounded generation.
• Fine-tune and evaluate embedding, reranking, and transformer-based models.
• Develop evaluation frameworks and golden datasets using metrics such as NDCG, MRR, Recall@K, Precision@K, faithfulness, and hallucination rate.
• Analyze search logs, user behavior, and relevance data to identify opportunities and continuously improve search quality.
• Work closely with Search and Software Engineers to optimize OpenSearch/Elasticsearch and production retrieval systems.
• Take ML solutions from prototype to production, optimizing for relevance, latency, scalability, and reliability.

Key Areas of Ownership

Search Relevance | Retrieval | Ranking & Reranking | Query Understanding | Semantic Search | Embeddings | RAG | LLM Evaluation | Search Quality

What You Bring

• Strong foundation in Machine Learning, NLP, Information Retrieval, and Search Relevance.
• Strong Python programming skills with hands-on experience in PyTorch or TensorFlow.
• Experience with Hugging Face Transformers, Sentence Transformers, and Scikit-Learn.
• Practical experience with embeddings, vector search, BM25, ranking, reranking, and transformer models.
• Experience building, evaluating, and deploying production ML systems.
• Strong analytical skills and ability to translate complex search/retrieval problems into measurable improvements.

Good to Have

• Experience with RAG, LLM applications, prompt engineering, and LLM evaluation.
• Hands-on experience with OpenSearch/Elasticsearch.
• Experience with vector databases and large-scale retrieval systems.
• Experience working with search logs, clickstream data, relevance judgments, or recommendation systems.
• Knowledge of distributed systems and large-scale data processing.

Qualifications

• Bachelor's or Master's degree in Computer Science, AI, ML, Data Science, or a related field.
• Relevant experience in Machine Learning, NLP, Search, Information Retrieval, Recommendation, or Generative AI.

Impact

You will help build high-quality, scalable search and AI retrieval experiences where relevance, accuracy, grounding, and speed directly impact the user experience.

You will have end-to-end ownership—from research and experimentation to production deployment and continuous optimization.