Hybrid
Full-Time
Noida, Uttar Pradesh
India
Skills
Amazon Web Services (AWS)
Artificial Intelligence (AI)
Kubernetes
Computer Science
Large Language Models (LLM)
Continuous Integration (CI)
Cloud Infrastructure
Cloud Computing
Troubleshooting
Infrastructure
About the Role
Company Description
ParfaitTu is a platform that utilizes diverse written forms like quotes, fables, and poems to encourage reflection on personal values and priorities. It aims to help individuals resist short-term temptations and focus on long-term gains in their personal, professional, and academic lives. The platform draws inspiration from ancient Greek concepts like Paideia, Arete, Phronesis, Ethike, and Eudaimonia to foster moral and intellectual growth.
We are looking for an AI Infrastructure Engineer to design and maintain the backbone of our AI-driven decision support agent. This role will focus on integrating advanced language models, optimizing Retrieval-Augmented Generation (RAG), structuring robust databases, and ensuring high retrieval accuracy. The ideal candidate has a strong background in cloud infrastructure, database management, and AI/ML engineering, with hands-on experience in large language model (LLM) integration and optimization.
Responsibilities:
Integrate and manage multiple LLM APIs (e.g., OpenAI’s ChatGPT 3.5/4, Anthropic’s Claude, xAI’s Grok, etc.) within our platform to provide robust conversational and decision-support capabilities.
Design, structure, and manage databases for efficient storage and retrieval of structured and unstructured data, ensuring high recall and precision in AI-driven responses.
Implement vector databases and optimize retrieval mechanisms using embeddings (e.g., FAISS, Pinecone, Weaviate, ChromaDB) to improve accuracy in RAG-based solutions.
Fine-tune and customize large language models for our specific domain and business needs, improving performance, tone, or accuracy as required for commercial deployment.
Develop and maintain file parsing pipelines to process documents, PDFs, images, and other structured/unstructured data formats for embedding and retrieval.
Set up and maintain the cloud infrastructure (ESDS,AWS, GCP, or Azure) needed for AI operations, including servers, databases, and any microservices architecture, ensuring high availability and scalability. Transfer the setup from one service provider to another while maintaining a proper log.
Optimize AI model performance and cost-efficiency by monitoring usage, latency, and throughput, and implementing improvements such as caching, load balancing, or model optimization techniques.
Ensure efficient data processing pipelines for handling large datasets, enabling smooth ingestion, indexing, and retrieval for AI-powered decision-making.
Collaborate with software developers to integrate AI functionalities into the product seamlessly, and with data engineers to manage data pipelines for training or feeding the AI models.
Stay up-to-date with the latest advancements in LLMs, RAG, and AI model fine-tuning and recommend new technologies or models that could enhance our product’s capabilities.
Required Qualifications:
Expertise in cloud platforms like AWS, Google Cloud, or Azure, including deploying and managing resources (computing instances, containers, storage, etc.) for high-load applications.
Hands-on experience with large language model APIs and frameworks, such as OpenAI/ChatGPT, Hugging Face Transformers, or other NLP libraries to implement AI features.
Strong database design and management skills with experience in SQL and NoSQL databases (e.g., PostgreSQL, MongoDB, Firebase, DynamoDB, or equivalent).
Proficiency in vector databases (FAISS, Pinecone, Weaviate, ChromaDB) and knowledge of document embedding techniques for information retrieval.
Experience in fine-tuning or training machine learning models, particularly NLP/LLM models, using frameworks like PyTorch or TensorFlow.
Strong programming skills in Python (or similar languages) for building AI pipelines, with knowledge of relevant libraries (e.g., LangChain for RAG, HuggingFace, scikit-learn).
Familiarity with Retrieval-Augmented Generation (RAG) concepts – e.g., implementing search indexes and connecting them to LLMs for contextual responses.
Experience developing file parsing mechanisms to process and structure text from PDFs, Word docs, JSON, and other formats for embedding and retrieval.
Solid understanding of MLOps practices – versioning models, continuous integration for model training/deployment, and monitoring model performance in production.
Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or related fields, or equivalent practical experience in AI infrastructure and development.
Preferred Qualifications & Experience:
2+ years of previous experience working on AI-driven products or conversational AI systems in a production environment.
Knowledge of prompt engineering and strategies to optimize LLM output quality and relevance.
Experience with containerization and orchestration tools (Docker, Kubernetes) to deploy and manage AI services at scale.
Familiarity with data security and privacy best practices, especially when dealing with cloud-based AI services and sensitive data.
Contribution to or active use of open-source AI projects and tools.
Strong analytical and troubleshooting skills, with a proactive attitude towards learning and implementing new AI technologies.
📌 Location: Hybrid
📌 Compensation: 10% over the average of your last 10 paychecks
📌 Interview Process:
✅ Initial Screening + Sample Assignment
✅ Feedback + Offer
ParfaitTu is a platform that utilizes diverse written forms like quotes, fables, and poems to encourage reflection on personal values and priorities. It aims to help individuals resist short-term temptations and focus on long-term gains in their personal, professional, and academic lives. The platform draws inspiration from ancient Greek concepts like Paideia, Arete, Phronesis, Ethike, and Eudaimonia to foster moral and intellectual growth.
We are looking for an AI Infrastructure Engineer to design and maintain the backbone of our AI-driven decision support agent. This role will focus on integrating advanced language models, optimizing Retrieval-Augmented Generation (RAG), structuring robust databases, and ensuring high retrieval accuracy. The ideal candidate has a strong background in cloud infrastructure, database management, and AI/ML engineering, with hands-on experience in large language model (LLM) integration and optimization.
Responsibilities:
Integrate and manage multiple LLM APIs (e.g., OpenAI’s ChatGPT 3.5/4, Anthropic’s Claude, xAI’s Grok, etc.) within our platform to provide robust conversational and decision-support capabilities.
Design, structure, and manage databases for efficient storage and retrieval of structured and unstructured data, ensuring high recall and precision in AI-driven responses.
Implement vector databases and optimize retrieval mechanisms using embeddings (e.g., FAISS, Pinecone, Weaviate, ChromaDB) to improve accuracy in RAG-based solutions.
Fine-tune and customize large language models for our specific domain and business needs, improving performance, tone, or accuracy as required for commercial deployment.
Develop and maintain file parsing pipelines to process documents, PDFs, images, and other structured/unstructured data formats for embedding and retrieval.
Set up and maintain the cloud infrastructure (ESDS,AWS, GCP, or Azure) needed for AI operations, including servers, databases, and any microservices architecture, ensuring high availability and scalability. Transfer the setup from one service provider to another while maintaining a proper log.
Optimize AI model performance and cost-efficiency by monitoring usage, latency, and throughput, and implementing improvements such as caching, load balancing, or model optimization techniques.
Ensure efficient data processing pipelines for handling large datasets, enabling smooth ingestion, indexing, and retrieval for AI-powered decision-making.
Collaborate with software developers to integrate AI functionalities into the product seamlessly, and with data engineers to manage data pipelines for training or feeding the AI models.
Stay up-to-date with the latest advancements in LLMs, RAG, and AI model fine-tuning and recommend new technologies or models that could enhance our product’s capabilities.
Required Qualifications:
Expertise in cloud platforms like AWS, Google Cloud, or Azure, including deploying and managing resources (computing instances, containers, storage, etc.) for high-load applications.
Hands-on experience with large language model APIs and frameworks, such as OpenAI/ChatGPT, Hugging Face Transformers, or other NLP libraries to implement AI features.
Strong database design and management skills with experience in SQL and NoSQL databases (e.g., PostgreSQL, MongoDB, Firebase, DynamoDB, or equivalent).
Proficiency in vector databases (FAISS, Pinecone, Weaviate, ChromaDB) and knowledge of document embedding techniques for information retrieval.
Experience in fine-tuning or training machine learning models, particularly NLP/LLM models, using frameworks like PyTorch or TensorFlow.
Strong programming skills in Python (or similar languages) for building AI pipelines, with knowledge of relevant libraries (e.g., LangChain for RAG, HuggingFace, scikit-learn).
Familiarity with Retrieval-Augmented Generation (RAG) concepts – e.g., implementing search indexes and connecting them to LLMs for contextual responses.
Experience developing file parsing mechanisms to process and structure text from PDFs, Word docs, JSON, and other formats for embedding and retrieval.
Solid understanding of MLOps practices – versioning models, continuous integration for model training/deployment, and monitoring model performance in production.
Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or related fields, or equivalent practical experience in AI infrastructure and development.
Preferred Qualifications & Experience:
2+ years of previous experience working on AI-driven products or conversational AI systems in a production environment.
Knowledge of prompt engineering and strategies to optimize LLM output quality and relevance.
Experience with containerization and orchestration tools (Docker, Kubernetes) to deploy and manage AI services at scale.
Familiarity with data security and privacy best practices, especially when dealing with cloud-based AI services and sensitive data.
Contribution to or active use of open-source AI projects and tools.
Strong analytical and troubleshooting skills, with a proactive attitude towards learning and implementing new AI technologies.
📌 Location: Hybrid
📌 Compensation: 10% over the average of your last 10 paychecks
📌 Interview Process:
✅ Initial Screening + Sample Assignment
✅ Feedback + Offer