About the Role

We are looking for a highly skilled GenAI Engineer to design, develop, and optimize large-scale AI solutions leveraging LLMs, Retrieval-Augmented Generation (RAG), NLP, and advanced analytics techniques. The ideal candidate will have strong expertise in building intelligent AI applications, designing robust evaluation frameworks, and deploying scalable data processing pipelines using Python, PySpark, and SQL. Key Responsibilities

Retrieval-Augmented Generation (RAG) & NLP

Design and implement advanced RAG pipelines using vector databases, semantic search, and knowledge retrieval frameworks.

Develop and optimize NLP models for text processing, classification, summarization, information extraction, and conversational AI use cases.

Build intelligent retrieval systems leveraging embeddings, chunking strategies, reranking techniques, and contextual search.

Work with vector databases such as Pinecone, Weaviate, Chroma, FAISS, or Elasticsearch.

Prompt Engineering & Agentic AI

Develop and optimize sophisticated prompting techniques for improved LLM performance.

Implement function calling, tool usage, chain-of-thought workflows, and structured outputs to enable deterministic AI agent behavior.

Design and evaluate multi-agent and agentic AI frameworks.

Create guardrails, validation mechanisms, and monitoring frameworks for production-grade AI systems.

Statistical Modeling & Evaluation

Apply statistical methods and hypothesis testing to assess model performance and reliability.

Design evaluation frameworks using quantitative metrics to measure accuracy, relevance, hallucination rates, and user experience.





Build predictive models and data-driven approaches to enhance AI solution quality.

Conduct A/B testing and experiment design to optimize model performance.

Data Analysis & Feature Engineering

Perform exploratory data analysis (EDA) on structured and unstructured datasets.

Develop feature engineering and data synthesis techniques to improve training and evaluation datasets.

Analyze model outputs and user interactions to identify areas of improvement.

Create reusable data pipelines for AI model training, testing, and monitoring.

Data Engineering & Development

Develop scalable data processing solutions using Python, PySpark, and SQL.

Build ETL/ELT pipelines to support AI and analytics workloads.

Optimize data transformation and querying processes for large datasets.

Collaborate with Data Engineers, Data Scientists, Product Teams, and Business Stakeholders to deliver end-to-end AI solutions.

Required

Skills

4+ years of experience in Python and SQL.

Strong hands-on expertise in PySpark and distributed data processing.

Experience with LLMs, Generative AI, RAG architectures, and NLP techniques.

Expertise in Prompt Engineering, Function Calling, AI Agents, and Structured Outputs.

Strong understanding of Machine Learning, Statistics, Hypothesis Testing, and Model Evaluation.

Experience working with vector databases and semantic search technologies.

Hands-on experience with AI frameworks such as LangChain, LlamaIndex, DSPy, or similar.

Knowledge of REST APIs, microservices, and cloud-native deployments.

Solid analytical and problem-solving skills.

📌 Generative AI Engineer (Gurugram)
🏢 EXL
📍 Gurugram