[Remote] AI Platform Engineer

Note The job is a remote job and is open to candidates in USA. Annapurna is seeking a senior AI Platform Engineer who will be responsible for designing, building, and scaling production-grade AI solutions across the organization. The role involves developing AI agents, reusable components, and enterprise AI capabilities, while collaborating with various teams to implement AI strategies effectively. Responsibilities Design, build, and deploy production AI agents and AI-powered services Develop reusable AI components, frameworks, and workflows that can be leveraged across teams Prototype, validate, and productionize AI use cases from concept through deployment Create and maintain reference architectures and implementation patterns Integrate and optimize Large Language Models (LLMs) within enterprise applications Design and implement Retrieval-Augmented Generation (RAG) architectures and pipelines Develop prompt engineering frameworks, prompt versioning, testing, and evaluation processes Build agentic workflows and multi-step AI systems using orchestration frameworks Support engineering teams in implementing AI capabilities within their products and services Partner with development squads to accelerate AI adoption and best practices Contribute to AI-driven software development initiatives across the organization Help define and evolve AI engineering standards through practical implementation experience Establish AI observability, monitoring, evaluation, and performance measurement capabilities Implement AI cost tracking, governance, and operational controls Improve reliability, scalability, and maintainability of AI systems Support production troubleshooting and continuous optimization of AI solutions Work closely with the AI Platform Architect to align implementations with the broader AI strategy Collaborate with Compliance and ARX PS teams to ensure responsible and compliant AI deployment Co-own AI workflow platforms (e.g., n8n) alongside DevOps and Platform Engineering teams Provide implementation feedback that informs future platform standards and architectural decisions Skills 6-8+ years of software engineering experience in production environments Proven experience designing and delivering production AI solutions Experience building AI agents, autonomous workflows, or agentic systems Strong background integrating LLMs into enterprise applications and services Experience delivering end-to-end AI projects from prototype to production Advanced prompt engineering and prompt optimization skills Experience with Retrieval-Augmented Generation (RAG) architectures Experience with vector databases and semantic search technologies Strong API integration and orchestration experience Experience with workflow automation platforms (e.g., n8n, LangGraph, CrewAI, AutoGen, or similar) Knowledge of AI evaluation, testing, and observability practices Familiarity with cloud-native architectures and distributed systems Strong systems-thinking and architectural problem-solving capabilities Experience designing scalable, reliable, and maintainable software systems Strong understanding of software engineering best practices, including CI/CD, testing, and monitoring Ability to balance experimentation with production-grade engineering standards Company Overview At Annapurna, we are focused on becoming a trusted responsible search partner for our clients. It was founded in 2008, and is headquartered in London, England, GBR, with a workforce of 51-200 employees. Its website is https//www.annapurnarecruitment.com/.