Artificial Intelligence (AI) Engineer

Position: AI Engineer (Python, LLMs, Vector Databases, OCR, Image Generation)

Location: Remote (Delhi or Bengaluru)

About our Company

LM Solutions India Pvt. Ltd.

Our small but growing team of skilled professionals works closely with global clients to create engaging learning experiences and implement effective talent development strategies that drive real business outcomes.

We are also at the forefront of integrating AI into learning solutions. Our technology stack is built on Python, leveraging LlamaIndex to power our retrieval-augmented generation (RAG) pipelines with OpenAI and other large language models (LLMs). We work extensively with vector databases, optical character recognition (OCR) tools, and AI-driven image generation to transform document-based content into structured, interactive micro-learning experiences. While we don’t host or train our own AI models, we focus on seamlessly integrating best-in-class AI services into our workflows. As we continue to scale, we are seeking passionate individuals to help us enhance and expand our AI-powered capabilities.

Role & Responsibilities

·      Enhance and optimize our RAG pipeline, integrating various LLMs via Open AI and other  providers.

·      Work with vector databases (e.g., Pinecone, FAISS, We aviate, Milvus) to store and retrieve embeddings efficiently.

·      Implement OCR solutions to extract text from images (e.g., Tesseract, Azure/AWS OCR, Google Vision).

·      Integrate image generation models (e.g., Stable Diffusion, Open AI DALL·E) into our content pipeline.

·      Improve document parsing and content structuring using LlamaIndex.

·      Work within a cloud-based AI infrastructure (no on-prem hosting).

·      Collaborate with our product team to create AI-enhanced interactive learning experiences.

·      Ensure performance, scalability, and security of AI-driven workflows.

Requirements

·      Proficiency in Python and experience with AI/ML libraries (e.g., llama-index, langchain, transformers).

·      Hands-on experience with vector databases for similarity search.

·      Strong background in OCR technologies (e.g., Tesseract, AWS Textract, Google Vision, OpenCV).

·      Familiarity with image generation models (e.g., OpenAI DALL·E, Stability AI).

·      Experience integrating LLMs via APIs (Open AI, Anthropic, etc.).

·      Comfortable working with cloud-based AI services (AWS, Azure, GCP).

·      Strong problem-solving skills and the ability to work independently.

Nice-to-Have

·      Experience with document processing pipelines (e.g., PDFs, Word documents).

·      Background in AI-powered content recommendation or learning platforms.

·      Familiarity with serverless architectures (e.g., AWS Lambda, Azure Functions).