Job Summary :

We are looking for a skilled AI / LLM Engineer with hands-on experience in Generative AI, Prompt Engineering, and Large Language Model (LLM) application development. The ideal candidate should have expertise in building AI-powered solutions using leading LLM APIs, orchestrating workflows, processing unstructured data, and deploying scalable AI pipelines on cloud platforms.

Key Responsibilities :

- Design, develop, and optimize prompt engineering strategies for LLM-based applications.

- Build and maintain Generative AI solutions using leading LLM APIs such as OpenAI, Anthropic, and similar platforms.

- Develop AI workflows and Retrieval-Augmented Generation (RAG) pipelines using frameworks like LangChain and LlamaIndex.

- Process and analyze structured and unstructured data using Python, Pandas, and NumPy.

- Build document intelligence and NLP solutions for extracting, transforming, and analyzing information from various data sources.

- Implement vector search and embedding solutions using vector databases such as FAISS, Pinecone, ChromaDB, or similar technologies.

- Design AI evaluation frameworks to measure model quality, reliability, and performance.

- Develop mechanisms for hallucination detection, drift monitoring, confidence scoring, and AI output validation.

- Work with human-in-the-loop (HITL) systems and annotation workflows to continuously improve model accuracy.

- Build, deploy, and maintain AI pipelines and REST APIs in cloud environments.

- Collaborate with cross-functional teams to integrate AI solutions into enterprise applications.

- Follow best practices for code quality, version control, CI/CD, and scalable AI deployment.

Required Skills & Qualifications :

- Experience in AI/ML, NLP, or Generative AI application development.

- Strong experience in Prompt Engineering and LLM-based application development.

- Hands-on experience with LLM APIs such as OpenAI, Anthropic, or similar platforms.

- Proficiency in Python and data processing libraries including Pandas and NumPy.

- Experience with LangChain, LlamaIndex, or equivalent AI orchestration frameworks.

- Strong understanding of NLP, document intelligence, and unstructured data processing.

- Experience with vector databases and embedding models (FAISS, Pinecone, Weaviate, ChromaDB, Milvus, etc.).

- Knowledge of AI evaluation methodologies, hallucination detection, drift monitoring, and confidence scoring.

- Experience building AI pipelines, APIs, and cloud-native applications.

- Familiarity with AWS, Azure, or GCP cloud platforms.

- Working knowledge of Git, CI/CD pipelines, and software development best practices.

Preferred Qualifications :

- Experience with Retrieval-Augmented Generation (RAG) architectures.

- Exposure to MLOps, model monitoring, and AI governance frameworks.

- Experience with annotation tools and human feedback loops for model improvement.

- Knowledge of containerization technologies such as Docker and Kubernetes is an added advantage.

- Excellent analytical, problem-solving, and communication skill