AI Engineer

Role Overview

We are looking for an experienced AI Engineer with strong hands-on expertise in LLMs, RAG, Agentic AI, Python, vector databases, and document intelligence. The ideal candidate will have experience building production-ready Generative AI applications, implementing LLM agents and retrieval pipelines, processing complex documents, and deploying AI solutions to cloud environments.

Responsibilities

• Design and implement LLM-powered agents with tool/function calling, dialogue state management, guardrails, and safety mechanisms.
• Build production-grade Retrieval-Augmented Generation (RAG) pipelines.
• Develop indexing, document chunking, embeddings, reranking, and hybrid retrieval solutions.
• Ingest, parse, and process complex PDFs and enterprise documents using OCR and multimodal LLMs.
• Design and continuously improve prompts, prompt templates, and system instructions.
• Conduct A/B testing and automated evaluations of LLM applications.
• Measure and optimize AI application quality across grounding, hallucination, accuracy, latency, and cost.
• Integrate LLM applications with external tools, APIs, and enterprise systems using Model Context Protocol (MCP).
• Deploy and monitor AI applications in AWS, Azure, or GCP environments.

Requirements

• 3+ years of experience building ML/AI applications.
• At least 1–2+ years of hands-on experience with LLMs and RAG.
• Strong programming expertise in Python.
• Hands-on experience with LangChain and/or LlamaIndex.
• Experience with Hugging Face and LLM APIs.
• Experience with vector databases such as Qdrant, Milvus, or Elasticsearch.
• Practical expertise in document chunking, embedding models, and reranking.
• Experience with OCR, table extraction, and multimodal document understanding.
• Experience deploying AI applications on AWS, Azure, and/or GCP.

Skills

• Python
• LangChain
• LlamaIndex
• Vector Databases
• AWS

Nice to Have

• Strong understanding of emerging developments in Generative AI and Agentic AI.
• Experience implementing AI guardrails and responsible AI practices.
• Experience optimizing LLM applications for accuracy, latency, and cost.
• Experience working in the pharmaceutical industry.