Senior AI Engineer Agentic AI / Generative AI / LLM

Senior AI Engineer Agentic AI / Generative AI / LLM

Position: Senior AI Engineer

Location: Remote

Experience: 8+ Years Software Engineering | 3+ Years GenAI/LLM Engineering

Position Overview

We are seeking an experienced Senior AI Engineer to design, develop, deploy, and support enterprise-grade Generative AI and Agentic AI solutions.

The ideal candidate will have strong hands-on expertise in LLM orchestration, Agentic AI, Retrieval-Augmented Generation (RAG), Python, and LLM evaluation frameworks. This role requires experience taking AI solutions from initial architecture and development through production deployment, optimization, and ongoing support within enterprise or regulated environments.

Key Responsibilities

• Design and develop enterprise-grade Agentic AI and LLM-based applications using frameworks such as LangChain and LangGraph.
• Build multi-step LLM workflows, including orchestration, tool/function calling, structured outputs, retries, and error handling.
• Develop and optimize RAG pipelines, embeddings, vector search, indexing, and retrieval strategies.
• Design and implement LLM evaluation frameworks, golden datasets, quality metrics, and regression testing.
• Develop scalable AI applications and APIs using Python 3.11+, FastAPI, and Pydantic.
• Implement AI observability, tracing, structured logging, performance monitoring, and cost optimization using Datadog and OpenTelemetry.
• Deploy and maintain production AI applications, ensuring reliability, scalability, security, and performance.
• Conduct model benchmarking, fine-tuning, experimentation, and optimization.
• Collaborate with Product, Business, Risk, Compliance, and Security teams to translate business requirements into AI solutions.
• Provide production support, incident management, root-cause analysis, and continuous improvement.
• Mentor junior engineers and contribute to architecture, code reviews, and engineering best practices.

Required Technical Skills

• Agentic AI & LLM Frameworks: LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, or Amazon Bedrock Agents.
• Generative AI / LLMs: Enterprise LLM application development, orchestration, prompt engineering, and tool calling.
• RAG: Embeddings, vector databases, indexing, retrieval optimization, and document-based AI solutions.
• Programming: Strong Python 3.11+, asynchronous programming, type annotations, automated testing, FastAPI, and Pydantic.
• LLM Evaluation: Golden datasets, evaluation metrics, LLM-as-a-Judge, evaluation frameworks, and regression testing.
• Cloud & AI Platforms: Hands-on experience with enterprise cloud AI services, preferably Azure AI technologies and/or AWS AI services.
• Observability: Datadog, OpenTelemetry, tracing, logging, AI quality monitoring, and cost monitoring.
• Database: PostgreSQL, Aurora PostgreSQL, and vector database extensions.
• DevOps: Kubernetes, Helm, Terraform, CI/CD, and Apache Kafka.

Mandatory Experience

• 8+ years of professional software engineering experience.
• 3+ years of hands-on Generative AI / LLM application development.
• Strong implementation experience in Agentic AI and LLM orchestration, particularly LangChain.
• Demonstrated experience deploying at least one enterprise-grade GenAI/LLM application into production.
• Experience supporting live production AI applications, including incident response, performance optimization, and regression management.
• Strong understanding of enterprise security, access control, data governance, and compliance requirements.

Preferred Qualifications

• Experience in Financial Services, Banking, Insurance, Healthcare, or other regulated industries.
• Strong Azure AI implementation experience.
• Document AI / Intelligent Document Processing, OCR, and structured data extraction.
• Human-in-the-loop AI workflows and confidence-based automation.
• Experience with model benchmarking, fine-tuning, distillation, and optimization.
• Experience designing scalable, event-driven enterprise AI architectures.