Description

• Design and implement LLM-powered features using models like Gemini, LLaMA, or lighter BERT variants
• Build and optimize RAG (Retrieval-Augmented Generation) pipelines, vector stores, and embedding systems.
• Fine-tune or adapt foundation models using PEFT techniques to meet the needs of use cases.
• Define and conduct evaluations, address losses, deploy and monitor LLM applications in production.
• Collaborate cross-functionally with product, infra, and domain teams to ship end-to-end solutions.
• Influence technical decisions and roadmap. Guide junior team members
• Stay current with new developments in the LLM technical landscape and help us productionize new capabilities quickly and safely.

• 5+ years of hands on experience in ML with 3+ years of experience as an NLP Engineer
• Strong hands-on experience in developing and deploying applications using a LLM using common tuning methods.
• High proficiency in Python and deep learning libraries
• Experience deploying and monitoring ML systems in production
• Strong product sense and interest in solving customer-facing problems.”
• Collaboration, initiative and motivation to handle ambiguity and progress with design and implementation.

• Fine-tune or adapt foundation models using PEFT techniques to meet the needs of use cases.
• Background in one or more of: NLU/NLG, document understanding, knowledge graphs, or multimodal learning.
• Experience in orchestration frameworks such as LangGraph
• Experience with Voice AI
• Experience as technical lead of an ML team.