ML / Fine-Tuning Engineer

What We Expect:

• Fine-tune open-source LLMs (Qwen, Llama) from experiment to production-ready checkpoint
  
• Run SFT and RL alignment (GRPO, DPO) to improve output accuracy
  
• Execute training on AWS GPU instances (p4d, p5, g5) using distributed training
  
• Diagnose/fix training issues: loss imbalances, OOM errors, gradient instabilities
  
• Collaborate with evaluation and data engineering to iterate on quality gaps
  
• Make data-driven model scaling decisions (8B → 14B → 70B) based on offline metrics
  

Requirements

• Experience: 5+ years ML engineering, with 2+ years in LLM fine-tuning
  
• LLM Models: Hands-on with open-source LLMs — Qwen and Llama required
  
• Training Methods: SFT, LoRA/QLoRA, GRPO, DPO/RLHF
  
• Frameworks: NVIDIA NeMo/NeMoRL, VeRL, HuggingFace TRL — must have used at least two
  
• Distributed Training: DeepSpeed ZeRO, FSDP2, multi-node GPU orchestration
  
• AWS Infrastructure: p4d/p5/g5 GPU instances, SageMaker Training Jobs
  
• Languages: Python, PyTorch; CUDA debugging a plus
  

Preferred (Not Required): Fine-tuning for tool-calling/agent tasks; multi-node GRPO/RLHF with NeMoRL or VeRL; tokenizer internals and chat-template rendering for tool-use formats.

Benefits

• Comprehensive Medical Coverage:
  Health insurance of INR 5.0 Lakhs for you and your family (up to 6 members), ensuring complete peace of mind.
• Robust Protection Plans:
  Group Personal Accident Insurance and Group Term Life Insurance to safeguard you and your loved ones.
• Retirement Benefits:
  PF and Gratuity provided as per standard government regulations.
• Flexible Work Options:
  Enjoy hybrid work arrangements & flexible working hours.
• Generous Leave Policy:
  21 days of annual leave, in addition to 10 company-declared holidays.
• Employee Well-being Spaces:
  Access to a dedicated break-out area with round-the-clock refreshments for relaxation and rejuvenation.