While technology is the heart of our business, a global and diverse culture is the heart of our success. We love our people and we take pride in catering them to a culture built on transparency, diversity, integrity, learning and growth.
If working in an environment that encourages you to innovate and excel, not just in professional but personal life, interests you- you would enjoy your career with Quantiphi!
Role: Machine Learning Engineer
Experience Level: 2+ Years
Work location: Mumbai, Bangalore & Trivandrum
Notice Period: 0- 15 days
Role & Responsibilities:
Develop and optimize "Agentic" workflows for complex business processes like Buyer Automation and Hour Meter extraction.
Implement advanced RAG (Retrieval-Augmented Generation) and tool-calling capabilities to enable agents to interact with external APIs and databases.
Experience with high-reasoning models like Claude 3.5 Sonnet, with open-weight alternatives (Llama 3.1) for cost and performance optimization.
Develop robust benchmarking and evaluation pipelines using frameworks like LangSmith or RAGAS to track extraction accuracy.
Fine-tune and prompt-engineer models to handle specific industrial data formats and unstructured documents.
Collaborate with Data Engineers to build seamless data pipelines that feed into agentic reasoning modules.
Optimize model latency and token consumption to ensure scalable and cost-effective deployments.
Skills expectation:
Expertise in LLM Orchestration patterns (ReAct, Chain-of-Thought, multi-agent collaboration).
Deep experience with Azure AI services, including AI Search, AI Foundry, and Azure OpenAI.
Strong background in software architecture, including microservices and event-driven patterns (Azure Service Bus).
Proficiency in Python, advanced prompt engineering and techniques ML frameworks (PyTorch, TensorFlow).
Experience with AI Governance, compliance, and risk mitigation strategies.
Expert-level knowledge of LangChain, LangGraph, or Haystack.
Hands-on experience with vector databases and semantic search optimization.
Proven experience in deploying and monitoring LLMs in a production environment.
Implement tool-calling functions for agents using Playwright or Selenium to navigate and extract data from vendor portals lacking native APIs.
Develop the logic for the Streamlit-based review application to present agent outputs to business users.
Familiarity with containerization (Docker, Kubernetes) for ML model serving.
If you like wild growth and working with happy, enthusiastic over-achievers, you'll enjoy your career with us!
