LLM Post-Training Engineer
Core
Design and execute post-training strategies (SFT, RLHF, policy-reward) to transform foundation models into domain-aligned agents for Customer Support and Network Deployment in telecommunications.
Role type
Senior IC LLM Post-Training Engineer
Builds
Production-ready, domain-aligned LLM agents for autonomous network operations and customer support
Domain
Telecommunications (Network Deployment, RAN) + Large Language Models
Deliverable
production ML models
Required skills
LLM fine-tuning (SFT, LoRA, QLoRA), Policy-reward training (GRPO, SAPO, DPO, PPO), Automated data curation, Synthetic data generation, Experiment tracking, Distributed training infrastructure, Model evaluation
Preferred skills
Telecommunications/RAN domain knowledge
Technologies
LoRA, QLoRA, GRPO, SAPO, DPO, PPO, GPU clusters
Responsibilities
Design and execute supervised fine-tuning pipelines; Implement policy-reward training using advanced optimization methods; Build automated pipelines for dataset curation and synthetic data generation; Manage end-to-end training runs and experiment tracking
Seniority
Senior, hands-on IC
