AI / ML Engineer (Agentic AI & Prompt Engineering)

We are seeking a senior-level AI/ML Engineer with extensive expertise in Agentic AI and Prompt Engineering to design, deploy, and scale advanced AI solutions. This role focuses on translating cutting-edge Large Language Model (LLM) patterns into robust production systems. The ideal candidate brings 8+ years of software engineering and machine learning experience, specializing in complex prompt optimization (zero-shot, few-shot, ReAct, chain-of-thought), Retrieval-Augmented Generation (RAG) architectures, and vector database integrations.

Key Responsibilities:

• Design, optimize, and chain complex structured prompts using advanced techniques (ReAct, self-consistency, decomposition, and verification strategies).

• Build and maintain production-ready Retrieval-Augmented Generation (RAG) pipelines leveraging modern embedding models, vector search, and context management.

• Integrate LLM workflows and agentic capabilities seamlessly into core application architectures via REST APIs.

• Establish guardrails, safety mechanisms, compliance protocols, and evaluation frameworks for conversational and autonomous AI flows.

• Preprocess multi-modal data, engineer features, and optimize end-to-end ML models from design through production deployment.

Required Skills & Qualifications:

• 8+ years of experience in AI/ML software engineering with a strong emphasis on LLMs and generative systems.

• Production experience with major foundation models (OpenAI, Anthropic, LLaMA, Mistral, Gemini) and knowledge of tokenization, reasoning patterns, and model behaviors.

• Deep understanding of RAG components, including vector databases (e.g., FAISS, Milvus, Pinecone), chunking strategies, and embedding models.

• Advanced Python expertise and hands-on experience integrating LLM capabilities into RESTful service architectures.

• Solid understanding of core software development hygiene, including version control (Git), API contracts (JSON, YAML), and experiment tracking.

Preferred Qualifications:

• Background in Computer Vision architectures and image processing projects.

• Hands-on experience with modern deep learning frameworks such as PyTorch or TensorFlow.

• Exposure to enterprise MLOps tools, continuous integration pipelines, and cloud platform infrastructure.