P1C1TSTS.Understand the current legacy system and architect, scale Agentic AI systems capable of multi-step reasoning and autonomous action for application modernization.Define reference architectures for container-based app hosting, memory management (vector DBs), and robust data pipelines.Lead the product vision for reusable AI modules, including RAG (Retrieval-Augmented Generation), hybrid ML/LLM systems, and standardized evaluation frameworks.Evaluate and select the LLM stack (models, orchestration frameworks, and observability tools) based on cost, latency, and performance.Standardize advanced prompting patterns, including chain-of-thought, few-shot templates, and automated chunking strategies to optimize for accuracy and cost.Drive team productivity by implementing and championing AI-assisted coding workflows (e.g., GitHub Copilot, Claude Code) to accelerate the Development & migration project.Embed LLM workflows into existing enterprise systems, ensuring seamless interoperability and high-performance output.Collaborate with security teams to enforce AI safety, data privacy, and ethical AI practices.Recruit, coach, and lead a high-performing GenAI engineering team, fostering a culture of continuous learning.Serve as the primary SME for post-sale customer engagements and internal leadership, translating complex AI concepts into actionable business strategies10+ years of experience in AI/ML engineering with 1+ years in agentic AI and LLM systemsHands-on development experience using Github Copilot, Claude Code for rapid AI prototyping and implementationExpertise in any of the cloud platform (AWS / Azure / Google Cloud Platform)Strong proficiency in LangGraph, LangMem, and agentic workflow developmentExperience with reasoning, instruct, safety & embedding modelsExtensive experience in LLM evaluation and testing (LangGraph evals, Agent evals, DeepEval, prompt testing frameworks)
Never miss an opportunity! Create an alert based on the job you applied for.
