Job Description
📋 Description Architect and implement production-ready AI solutions with LLMs, transformers, and retrieval systems. Design prompts, workflows, and RAG pipelines to improve accuracy, cost, latency, and safety. Build multi-step agentic systems that invoke tools/APIs, manage state, and robustly reason. Deploy GenAI pipelines in production (API, batch, streaming) with reliability and scalability. Build and maintain evaluation frameworks for grounding, factuality, latency, and cost. Develop guardrails for prompts, content moderation, tool limits, and state validation. 🎯 Requirements 3+ years post-education ML with NLP/transformers/generative AI. Hands-on with LLM libraries (LangChain, LlamaIndex, OpenAI API) and services (Azure/AWS). Experience designing multi-step agent systems with tool calls and safeguards. Production deployment of ML models via API, batch, or streaming. Python proficiency; production-grade, modular code; CI/CD familiarity. Degree in CS/Data Science/Engineering or equivalent experience. 🎁 Benefits Competitive benefits package (medical, dental, vision). 401K, PTO, paid holidays, commuter benefits. Life Insurance and disability coverage. EAPs and other wellness programs.
