Overview

Quantiphi is an award-winning Al-first digital engineering company driven by the desire to solve transformational problems at the heart Of business.

Responsibilities

• Designing and developing advanced machine learning models and algorithms to solve complex business problems.
• Optimizing and deploying these models on AWS infrastructure, ensuring scalability and reliability.
• Design and implement agentic Al architectures using frameworks such as LangChain or Amazon Bedrock Agents, enabling autonomous task planning, decision-making, and mufti-step reasoning.
• Architect and deploy scalable Al solutions on AWS, leveraging services like Lambda, Bedrock, Step Functions, S3, API Gateway, in and SageMaker.
• Develop and maintain Model Context protocol (MCP) implementations to manage state, context windows, memory, and prompt orchestration across distributed agent systems.
• Integrate agentic workflows with LLMs (Titan, Nova, Cohere, Claude, etc.) via Bedrock, ensuring high-availability and multi-model support.
• Model Evaluation & Optimization: Evaluate LLM's zero-shot and few-shot capabilities, fine-tuning hyperparameters, ensuring task generalization, and exploring model interpretability for robust web app integration.
• Experience implementing secure, scalable APIs and integrating with 3rd-party data sources and tools.
• Ability to collaborate with cross-functional teams such as Developers, QA, Project Managers, and other stakeholders to understand their requirements and implement solutions.

Qualifications

• 8+ years of relevant hands-on technical experience implementing, and developing cloud ML solutions on AWS.
• 8+ years of relevant hands-on technical experience implementing, and developing cloud ML solutions on AWS.
• Hands-on experience on AWS Machine Learning services.
• Proven experience using AWS Sagemaker leveraging different types of data sources, Training jobs, real-time and batch Inference, and Processing Jobs.
• Natural Language Processing:
• Should have experience with Deep Learning Concepts - Transformers, BERT, Attention models.
• Strong programming skills in python and experience with NLP libraries such as Hugging Face Transformers, SpaCy, NLTK, or Stanford NLP.
• Strong understanding Of NLP concepts: tokenization, embeddings, syntactic and semantic parsing, named entity recognition, and coreference.
• Agentic Al:
• Design and implement agentic Al architectures using frameworks such as LangChain or Amazon Bedrock Agents, enabling autonomous task planning, decision-making, and mufti-step reasoning.
• Architect and deploy scalable Al solutions on AWS, leveraging services like Lambda, Bedrock, Step Functions, S3, API Gateway, in and SageMaker.
• Develop and maintain Model Context protocol (MCP) implementations to manage state, context windows, memory, and prompt orchestration across distributed agent systems.
• Integrate agentic workflows with LLMs (Titan, Nova, Cohere, Claude, etc.) via Bedrock, ensuring high-availability and multi-model support.
• Must have Hands-on experience fine-tuning large language models( LLM) and Generative Al (GAI), specifically LLama2.
• Familiarity with LLM tool use, prompt templating, vector stores (e.g., Opensearch, Pinecone, Elasticsearch, Bedrock KB), and context management.
• Model Evaluation & Optimization: Evaluate LLM's zero-shot and few-shot capabilities, fine-tuning hyperparameters, ensuring task generalization, and exploring model interpretability for robust web app integration.
• Experience with at least one of the workflow orchestration tools, Airflow, StepFunctions, SageMaker Pipelines, Kubeflow etc.
• Experience implementing secure, scalable APIs and integrating with 3rd-party data sources and tools.
• Ability to collaborate with cross-functional teams such as Developers, QA, Project Managers, and other stakeholders to understand their requirements and implement solutions.

Nice to have

• Experience of working for customers/workloads in the Edtech domain with use cases.
• Experience with software development.