
Senior AI Engineer, FDE Heavy
Posted 2 days ago

Posted 2 days ago
This is a fully remote position, open to applicants in India.
• Design, develop, and implement intricate multi-agent systems utilizing LangGraph, LangChain, or similar frameworks to streamline enterprise workflows and manage lengthy, asynchronous tasks.
• Assume full responsibility for the development of AI agents, encompassing system design, prompt engineering, tool integration, deployment, monitoring, assessment, and ongoing optimization.
• Convert complex and uncertain enterprise needs into tangible AI-driven solutions, agent behaviors, tool specifications, execution strategies, and dependable workflows.
• Collaborate closely with customers, product teams, and engineering stakeholders to grasp operational challenges and deliver AI applications ready for production.
• Create, construct, and enhance RAG pipelines by refining document chunking, embedding generation, retrieval strategies, reranking, and vector search efficiency.
• Establish automated evaluation frameworks to assess agent accuracy, hallucination rates, task completion, and overall system dependability.
• Connect AI agents with enterprise applications, databases, APIs, and existing technological infrastructure to facilitate intelligent automation and comprehensive task execution.
• Enhance model inference costs, response times, and system performance through appropriate model selection and effective orchestration strategies.
• Develop and enforce LLMOps best practices encompassing tracing, monitoring, debugging, version control, deployment, and production evaluation.
• Diagnose complex technical issues, pinpoint performance bottlenecks, and continually enhance AI systems based on actual usage and evaluation findings.
• Over 5 years of comprehensive software engineering experience, with substantial recent involvement in Applied AI, Generative AI, or Large Language Model (LLM)-based applications.
• Mastery of Python, with the capability to produce clean, modular, scalable, testable, and production-quality code.
• Significant hands-on experience in designing, constructing, and deploying production-ready LLM applications using LangChain, LangGraph, or comparable orchestration frameworks.
• Demonstrated experience in developing complex agentic workflows that involve multi-agent orchestration, tool invocation, state management, asynchronous execution, and extended tasks.
• Strong comprehension of RAG architectures, including document processing, chunking methodologies, embeddings, retrieval systems, reranking, and vector search optimization.
• Experience in building automated LLM evaluation pipelines to evaluate output quality, accuracy, hallucination rates, task completion metrics, and system reliability.
• Capability to independently manage technical problem-solving and deliver comprehensive AI solutions in dynamic enterprise settings.
• Excellent collaboration and communication skills, with the ability to engage directly with stakeholders and convert business requirements into technical implementations.
• Proficient in Python.
• Familiar with LangChain.
• Knowledgeable in LangGraph.
• Competitive salary and performance-based bonuses.
• Opportunities for professional development and continuous learning.
• Flexible work environment and remote work options.
• Comprehensive health and wellness benefits.
• Collaborative and innovative team culture.
Huron
Amplified Industries, Inc.
HarperCollins Publishers
Get handpicked remote jobs straight to your inbox weekly.