Machine Learning Engineer

Senior Generative AI / Machine Learning Engineer

We are seeking an experienced Senior Generative AI / Machine Learning Engineer to design, develop, and deploy production-ready Generative AI solutions powered by Large Language Models (LLMs). The ideal candidate will have strong hands-on experience with Python, LLMs, LangChain, LangGraph, agentic AI workflows, LLM memory, retrieval pipelines, and machine learning engineering.

The candidate will work across the complete AI/ML lifecycle, including model evaluation and selection, solution design, development, deployment, monitoring, and optimization of scalable GenAI applications.

Key Responsibilities

• Design, develop, and productionize Generative AI applications using open-source and proprietary LLMs.
• Evaluate and integrate LLMs such as OpenAI, Anthropic, Llama, and Mistral based on business and technical requirements.
• Design and implement agentic AI workflows using LangChain and LangGraph.
• Develop multi-step AI orchestration workflows for complex business use cases.
• Implement short-term and long-term memory strategies for LLM-based applications.
• Design and manage state management and context-handling mechanisms for agentic systems.
• Optimize prompts, retrieval pipelines, context management, and orchestration logic.
• Develop and integrate RAG/retrieval-based solutions for enterprise GenAI applications.
• Develop machine learning models and production-ready AI/ML solutions where required.
• Build scalable and reliable AI services using Python and ML engineering best practices.
• Deploy, monitor, troubleshoot, and maintain AI/ML and GenAI systems in production environments.
• Collaborate with product, platform, data science, engineering, and business teams to deliver scalable AI solutions.
• Establish appropriate evaluation strategies to measure model quality, accuracy, performance, and reliability.
• Continuously research and evaluate emerging LLM, GenAI, and agentic AI technologies.

Required Skills

• 8–9 years of experience in Machine Learning, AI Engineering, Data Science, or related fields.
• Strong hands-on experience developing Generative AI and LLM-based applications.
• Strong experience with LLMs including OpenAI, Anthropic, Llama, Mistral, or comparable models.
• Hands-on experience with LangChain and/or LangGraph.
• Strong understanding of agentic AI architectures and workflows.
• Solid understanding of LLM memory architecture, state management, and context handling.
• Strong proficiency in Python.
• Experience with prompt engineering and optimization.
• Experience designing and optimizing retrieval/RAG pipelines.
• Strong understanding of machine learning concepts and ML engineering best practices.
• Experience deploying and supporting production-grade AI/ML systems.
• Strong analytical, troubleshooting, and problem-solving skills.

Nice-to-Have Skills

• Experience with Google Cloud Platform (GCP).
• Hands-on experience with Vertex AI, BigQuery, and Google Cloud Storage (GCS).
• Experience building and deploying ML models.
• Experience with MLOps and production model lifecycle management.
• Experience with model evaluation, monitoring, and observability.
• Experience with enterprise-scale GenAI implementations.
• Experience working with open-source LLM frameworks and models.

Roles & Responsibilities

• Lead end-to-end development of GenAI solutions from model selection through production deployment.
• Build agentic applications using LangChain/LangGraph.
• Implement memory and state management capabilities for LLM applications.
• Develop and optimize prompts, retrieval mechanisms, and AI orchestration workflows.
• Build ML models and integrate them into production AI solutions.
• Deploy and maintain scalable AI/ML applications.
• Monitor model and application performance and troubleshoot production issues.
• Collaborate with product and platform teams to translate business requirements into AI solutions.
• Evaluate new LLMs and GenAI technologies and recommend appropriate solutions.