Ir para o conteúdoIr para a pasta
  • Vagas
  • Empresas
  • Salários
  • Para empresas

      Avance em sua carreira

      Descubra qual pode ser seu salário, conquiste a vaga dos seus sonhos e compartilhe insights de qualidade de vida com sigilo.

      employer cover photo
      employer logo
      employer logo

      Mindfire Solutions

      Essa empresa é sua?

      Sobre
      Avaliações
      Remuneração e benefícios
      Vagas
      Entrevistas
      Entrevistas
      Buscas relacionadas: Avaliações da empresa Mindfire Solutions | Vagas da empresa Mindfire Solutions | Salários da empresa Mindfire Solutions | Benefícios da empresa Mindfire Solutions
      Entrevistas da empresa Mindfire SolutionsEntrevistas do cargo de Software Engineer - AI/ML da empresa Mindfire SolutionsEntrevista da empresa Mindfire Solutions


      Glassdoor

      • Sobre
      • Prêmios
      • Blog
      • Fale conosco

      Empresas

      • Conta gratuita de empresa
      • Área da empresa
      • Blog para empresas

      Informações

      • Ajuda
      • Regras da Comunidade
      • Termos de Uso
      • Privacidade e opções de anúncios
      • Não venda nem compartilhe minhas informações
      • Ferramenta de consentimento de uso de cookies

      Trabalhe conosco

      • Anunciantes
      • Carreiras
      Baixe o aplicativo:

      • Busque por:
      • Empresas
      • Vagas
      • Localizações

      Copyright © 2008-2026. Glassdoor LLC. “Glassdoor”, “Worklife Pro”, “Bowls” e o logotipo do Glassdoor são marcas comerciais pertencentes à Glassdoor LLC.

      Empresas seguidas

      Fique por dentro de todas as oportunidades e dicas internas seguindo as empresas de seus sonhos.

      Buscas de vagas

      Comece a buscar vagas para receber atualizações e recomendações personalizadas.

      Entrevista para Software Engineer - AI/ML

      10 de jan. de 2026
      Candidato(a) sigiloso(a) à entrevista
      Bhubaneshwar
      Nenhuma oferta
      Experiência negativa
      Entrevista fácil

      Candidatura

      Candidatei-me online. Fui entrevistado pela Mindfire Solutions (Bhubaneshwar) em jan. de 2026

      Entrevista

      i applied in their portal ,from application to getting first call it took 3 weeks, the interview started with questions on langchain and langgraph, their differences, in langchain what design patterns are there, is the process syncronus or not, then came to a system design problem where they asked to implement a search functionality for a company, a order placing/ order status knowing, a enquiry feature , what will you use, how will you design the system

      Perguntas de entrevista [1]

      Pergunta 1

      question on langchain and langgraph, what is memory in langchain, what is state in langgraph
      Responder à pergunta

      Outras avaliações de entrevista de vagas de Software Engineer - AI/ML da empresa Mindfire Solutions

      Entrevista para Software Engineer - AI/ML

      24 de nov. de 2025
      Candidato(a) sigiloso(a) à entrevista
      Nenhuma oferta
      Experiência positiva
      Entrevista difícil

      Candidatura

      Candidatei-me online. Fui entrevistado pela Mindfire Solutions em nov. de 2025

      Entrevista

      I applied online and was shortlisted for the initial technical discussion. The interview was conducted over Google Meet with senior members of the technical team and lasted for about 1 hour and 2 minutes. It was a single round but covered multiple areas including DSA (string compression, character frequency, list rotation) and an in-depth discussion on Generative AI topics such as RAG architecture, vector databases, semantic search, LangChain, agent tools, memory handling, and model evaluation. The format was fast-paced with around 40 technical questions, mostly rapid-fire and detail-oriented. I was also asked to write a few lines of code on Colab while sharing my screen. There were no behavioral or HR questions in this round. The communication was clear, and instructions were shared beforehand regarding setup and expectations. I received the outcome after the interview. The interview went significantly deeper than a typical 2–4 year role, with advanced questions on internal workings of RAG systems, vector indexing (HNSW/IVF), caching strategies, LangChain tool mechanics, and precision/recall evaluation. The pace and breadth made it challenging even for someone with hands-on GenAI experience.

      Perguntas de entrevista [1]

      Pergunta 1

      DSA questions - compress string (aaabbc --> a3b2c1) - char frequency in string - perform left rotation on a list by d, without using additional list Gen AI questions - Talk about recent gen ai project - Detailed question about RAG architecture ( pre processing, chunking, embedding, vector db) - How exactly storage and retrieval happens in vector db - Type of vector db and when to use which one - in memory vs persistent vector db - semantic search in detail, formula of cosin similarly - How to handle caching, if user uploads same file in a chatbot, how to handle - HNSW, IVF, what is the use and their working - HNSW available in which db - how you pass chat history to llm - how is chat history passed to llm in langchain - short term and long term memory, how to implement in langchain - how to build custom tools, in langchain / dspy/ crewai - tool decorator - how tool decorator uses docstring of tool function - Under the hood how tool decorator works - how to pass info like session ID to tool, and also not expose it to llm - how to pass tools to an agent - if a value is not passed by llm how to get that in the tool, will it fail? - LangGraph basics - Pydantic and its uses - what llms have you worked with (list all models / versions, eg: gpt 4 --> gpt 4.1 , 4o, 4 mini etc, gemini--> 1.5 flash 1.5 pro etc) - open source models - hugging face vs ollama - How to handle a CSV file in RAG - how to handle the table data (unstructured.io) - have you tried mistral for extracting table? - pypdf, pdfplumber and what other libraries have you tried for table extraction, which works best? - how to make image embeddings, what model is used - multimodal llms (take image/ audio/video/ file as input, and gives multimodal output) - Talk about any other project of yours - Few questions related to project - Have you also worked on ML models apart from gen ai? - How do you evaluate RAG? - What is precision and recall in RAGAS, also in ML, formula and definition - Any questions for me..
      Responder à pergunta
      2