Overview
Job Description
We are seeking a Generative AI Engineer to design, build, and deploy advanced LLM-powered applications that solve real-world business problems. This role focuses on developing end-to-end Generative AI systems using modern foundation models, retrieval-augmented generation (RAG), and agent-based architectures.
The ideal candidate will work on integrating LLMs with structured and unstructured data sources such as PDFs, OCR outputs, APIs, and databases, while optimizing workflows for accuracy, latency, and cost. The role also involves developing prompt engineering strategies, building intelligent LLM agents with tool usage and memory, and continuously improving model outputs using automated and human-in-the-loop evaluation methods.
Key Responsibilities
- Design and build LLM-based applications using models such as GPT, LLaMA, Mistral, Claude, etc.
- Implement Retrieval-Augmented Generation (RAG) systems using vector databases (FAISS, Milvus, Pinecone, Weaviate, etc.).
- Develop prompt engineering strategies, prompt templates, and evaluation techniques.
- Build LLM agents with tool/function calling, multi-step reasoning, and memory.
- Integrate LLMs with structured and unstructured data sources (PDFs, OCR output, APIs, databases).
- Optimize LLM workflows for latency, cost, and accuracy.
- Evaluate and improve model outputs using automated and human-in-the-loop feedback.
- Secondary – Classical Machine Learning.
- Apply traditional ML techniques (classification, regression, clustering, ranking) where required.
- Work with feature engineering, data preprocessing, and model evaluation metrics.
- Integrate ML model outputs with GenAI pipelines (e.g., scoring, prioritization, risk signals).
- Understand trade-offs between ML models and LLM-based approaches.
- Optional – MLOps / Deployment.
- Containerize and deploy models and services using Docker (Kubernetes is a plus).
- Set up basic monitoring for model performance, drift, and failures.
- Work with CI/CD pipelines for AI services.
- Manage model versions and experiment tracking (MLflow, Weights & Biases, etc.).
UNIPREP is recruitment partner assisting hiring for Talent vesta consulting pvt ltd
Please apply on the link given