Job Description
Architect, implement, and deploy production-ready AI solutions using LLMs, transformer-based models, retrieval systems, and agentic workflows.
Design, iterate, and optimize prompts, workflows, and RAG pipelines to improve accuracy, latency, cost-efficiency, and safety.
Build multi-step agentic systems capable of task decomposition, tool and API invocation, state management, and robust reasoning chains.
Deploy and maintain GenAI pipelines across API, batch, and streaming production environments, ensuring reliability and scalability.
Develop and maintain evaluation frameworks to measure grounding, factuality, latency, and cost of AI systems.
Implement guardrails and safeguards, including prompt-injection protection, content moderation, output validation, loop prevention, and tool-call limits.
Collaborate cross-functionally with Product, Engineering, and ML Ops tea...
Ready to Apply?
Take the next step in your AI career. Submit your application to Blend360 today.
Submit Application