Design, implement, and ship AI-first product capabilities end-to-end from rapid prototype to production, spanning LLM-powered services, retrieval/grounding pipelines, and intelligent UX experiences. Own implementation across the full stack integrating front-end experiences, back-end services, and AI orchestration layers that connect models, context, and tools to deliver cohesive, extensible, high-performance recommendation systems. Instrument and evaluate AI features with telemetry, experimentat…
Responsibilities
Collaborate with design, research, and platform teams to adapt or fine-tune LLMs/SLMs for follow-on scenarios. Build agentic, tool-using workflows that reason across data and services; optimize for security, safety, latency, reliability, and cost efficiency. Contribute to engineering excellence secure-by-design, accessibility compliance, automated testing, and code craftsmanship across the product lifecycle.
Required Qualifications
Bachelor's Degree in Computer Science or related technical field AND 4+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience, and experience with generative AI. Drive experimentation through A/B testing and offline evaluation to evaluate system performance Comfortable driving complex server and client architecture across large product teams. Hands-on experience with modern LLM evaluation techniques, including LLM-as-a-Judge, agentic evaluations and RAG assessments. A track record of delivering successful, large scale applied ML projects in an industry setting. Experience with MLOps practices, model versioning, automated testing, monitoring and CI/CD for machine learning. Experience with proficient coding, debugging, and problem-solving skills. Outstanding communication and collaboration skills.
Original Posting
This role is sourced from Microsoft. Apply on Microsoft careers page