Job description🚀 𝐖𝐞’𝐫𝐞 𝐇𝐢𝐫𝐢𝐧𝐠 | 𝐀𝐈 / 𝐌𝐋 𝐏𝐥𝐚𝐭𝐟𝐨𝐫𝐦 𝐄𝐧𝐠𝐢𝐧𝐞𝐞𝐫 We are looking for a highly skilled AI/ML Platform Engineer to design, build, and scale AI-powered services, LLM-driven workflows, and intelligent systems powering Reachware’s next-generation platform. This role sits at the intersection of backend engineering, applied AI, and workflow orchestration. 🔧 𝐊𝐞𝐲 𝐑𝐞𝐬𝐩𝐨𝐧𝐬𝐢𝐛𝐢𝐥𝐢𝐭𝐢𝐞𝐬 𝐀𝐈 𝐒𝐞𝐫𝐯𝐢𝐜𝐞𝐬 & 𝐀𝐏𝐈𝐬: ‣ Design and develop AI-powered services using Python and FastAPI ‣ Build APIs for AI capabilities such as classification, summarization, enrichment, and document processing ‣ Implement multi-tenant AI endpoints with governance, quotas, and policy controls 𝐋𝐋𝐌 𝐖𝐨𝐫𝐤𝐟𝐥𝐨𝐰𝐬 & 𝐀𝐩𝐩𝐥𝐢𝐞𝐝 𝐀𝐈: ‣ Design and integrate LLM workflows within event-driven and Temporal-based systems ‣ Develop prompt engineering strategies and tool usage patterns for reliable AI outputs ‣ Implement human-in-the-loop systems, retries, safeguards, and failure handling 𝐄𝐦𝐛𝐞𝐝𝐝𝐢𝐧𝐠𝐬, 𝐑𝐞𝐭𝐫𝐢𝐞𝐯𝐚𝐥 & 𝐂𝐨𝐧𝐭𝐞𝐱𝐭: ‣ Build embedding pipelines and retrieval systems for intelligent search and context-aware AI ‣ Work with vector databases and systems like PostgreSQL, MongoDB, and Elasticsearch ‣ Ensure safe context handling, relevance tuning, and tenant isolation 𝐄𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 & 𝐎𝐛𝐬𝐞𝐫𝐯𝐚𝐛𝐢𝐥𝐢𝐭𝐲: ‣ Design evaluation frameworks for AI quality, latency, cost, and reliability ‣ Implement logging, tracing, and monitoring for AI services ‣ Continuously monitor and improve model performance, prompt quality, and system behavior 𝐂𝐨𝐥𝐥𝐚𝐛𝐨𝐫𝐚𝐭𝐢𝐨𝐧 & 𝐒𝐭𝐚𝐧𝐝𝐚𝐫𝐝𝐬: ‣ Collaborate with platform, integration, and product teams to embed AI into workflows ‣ Contribute to AI engineering standards, governance, and best practices ‣ Mentor engineers and drive adoption of AI capabilities across the platform 🧠 𝐌𝐮𝐬𝐭-𝐇𝐚𝐯𝐞 𝐒𝐤𝐢𝐥𝐥𝐬 ‣ 5+ years of software engineering experience with 2–3+ years in AI/ML/LLM systems ‣ Strong experience in Python and FastAPI (or similar frameworks) ‣ Hands-on experience with LLM integration, prompt engineering, and AI workflows ‣ Experience with embeddings, vector search, and retrieval-augmented generation ‣ Familiarity with distributed systems, APIs, and backend architecture ‣ Experience with Docker, Kubernetes, and CI/CD pipelines ‣ Strong understanding of observability, evaluation, and AI system reliability ‣ Strong problem-solving and system design skills 🌟 𝐄𝐬𝐬𝐞𝐧𝐭𝐢𝐚𝐥 𝐌𝐢𝐧𝐝𝐬𝐞𝐭 & 𝐋𝐞𝐚𝐝𝐞𝐫𝐬𝐡𝐢𝐩 ‣ Ownership mindset for AI system quality, safety, and reliability ‣ Strong systems thinking across models, workflows, data, and infrastructure ‣ Focus on delivering production-grade AI capabilities with measurable impact ‣ Collaborative, innovative, and continuous learning approach 📍 𝐋𝐨𝐜𝐚𝐭𝐢𝐨𝐧: Hyderabad (On-Site) 🗓 𝐖𝐨𝐫𝐤 𝐖𝐞𝐞𝐤: Sunday – Thursday (Week-off: Fri & Sat) 📩 𝐀𝐩𝐩𝐥𝐲: ta@mindsuite.in 📞 𝐂𝐨𝐧𝐭𝐚𝐜𝐭: +91 9100005500