LLM Fine Tuning Expert

VARTIS Platforms

Mumbai

On-site

INR 4,000,000 - 9,000,000

Full time

4 days ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

VARTIS Platforms in Mumbai seeks an experienced ML/NLP engineer to lead model adaptation for Indic and code-mixed text, selecting base models and tailoring tokenizers. You will curate data from conversations, emails, and financial documents, including synthetic data from larger teacher models.

You will run continued pretraining, SFT, LoRA/QLoRA or full fine-tuning for text and multimodal models, and align with RLHF, reward modelling, DPO, or GRPO, with verifiable rewards for numeric finance

Qualifications

  • 3+ years in deep learning with models shipped to production, including at least one model of 1B+ parameters you trained end-to-end on multiple GPUs.
  • Hands-on with Hugging Face Transformers, PEFT, and TRL, or equivalents such as Unsloth, Axolotl, or TorchTune.
  • Post-training beyond SFT (RLHF, reward modeling, DPO, GRPO, or similar), with measured gains on held-out data.
  • Production inference experience on vLLM, Triton Inference Server, or a similar engine.
  • Clear written and verbal communication: you can turn training results into a one-page recommendation a business leader can act on.

Responsibilities

  • Select base models (Qwen, Llama, Gemma, Mistral, Indic models) and adapt tokenizers for Indic and code-mixed text.
  • Curate training data from conversations, emails, and financial documents, including synthetic data from larger teacher models.
  • Run continued pretraining, SFT, and LoRA/QLoRA or full fine-tuning for text and multimodal models.
  • Align models with RLHF, reward modelling, DPO, or GRPO, including verifiable rewards for numeric finance tasks.
  • Train at scale on multi-GPU, multi-node setups using FSDP, DeepSpeed, or Megatron with BF16/FP8.
  • Design evaluations covering accuracy, numeric hallucination, bias, and robustness; find weaknesses and fix them.
  • Build scalable inference pipelines on vLLM, Triton Inference Server, SGLang, or TensorRT-LLM, with quantization for low-latency voice use.
  • Work with product, data, and business teams to turn their problems into model specs and success metrics.

Skills

Deep learning production experience
Hugging Face Transformers
PEFT
TRL
RLHF / reward modeling / DPO / GRPO
Production inference on vLLM / Triton
Excellent communication
Python
AWS Cloud

Tools

Hugging Face Transformers
PEFT
TRL
DeepSpeed
vLLM
Triton Inference Server
Megatron

Job description

Responsibilities
  • Select base models (Qwen, Llama, Gemma, Mistral, Indic models) and adapt tokenizers for Indic and code-mixed text.
  • Curate training data from conversations, emails, and financial documents, including synthetic data from larger teacher models.
  • Run continued pretraining, SFT, and LoRA/QLoRA or full fine-tuning for text and multimodal models.
  • Align models with RLHF, reward modelling, DPO, or GRPO, including verifiable rewards for numeric finance tasks.
  • Train at scale on multi-GPU, multi-node setups using FSDP, DeepSpeed, or Megatron with BF16/FP8.
  • Design evaluations covering accuracy, numeric hallucination, bias, and robustness; find weaknesses and fix them.
  • Build scalable inference pipelines on vLLM, Triton Inference Server, SGLang, or TensorRT-LLM, with quantization for low-latency voice use.
  • Work with product, data, and business teams to turn their problems into model specs and success metrics.
Mandatory Skills
  • 3+ years in deep learning with models shipped to production, including at least one model of 1B+ parameters you trained end-to-end on multiple GPUs.
  • Hands-on with Hugging Face Transformers, PEFT, and TRL, or equivalents such as Unsloth, Axolotl, or TorchTune.
  • Post-training beyond SFT (RLHF, reward modeling, DPO, GRPO, or similar), with measured gains on held-out data.
  • Production inference experience on vLLM, Triton Inference Server, or a similar engine.
  • Clear written and verbal communication: you can turn training results into a one-page recommendation a business leader can act on.
Preferred Skills
  • Debugging distributed training: divergence, NaN loss, OOM, low GPU utilization, failed resume.
  • Building evaluation sets and analyzing model weaknesses such as bias and robustness.
  • Hindi, Hinglish, or other Indic language modelling.
  • Financial data: bank statements, bureau reports, and credit or collections conversations.
  • Knowledge distillation, quantization, and inference optimization.
  • Speech or speech-to-speech models.
  • Open-source contributions or published checkpoints. Experience working with business or customer-facing teams.
  • Required Skills: Python, AWS Cloud.
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

LLM Finetuning Expert
LLM Finetuning Expert

LenDenClub • Mumbai

On-site
INR 3,000,000 - 5,000,000
Senior AI/ML Data Scientist or Engineer - LLM Fine-Tuning, Evaluation & Inference
Senior AI/ML Data Scientist or Engineer - LLM Fine-Tuning, Evaluation & Inference

Vamstar • India

On-site
INR 600,000 - 1,200,000
AI/ML Engineer
AI/ML Engineer

National e-Governance Division • New Delhi

On-site
INR 1,500,000 - 2,100,000
LLM Engineer (Large Language Models)
LLM Engineer (Large Language Models)

Fospe UK Ltd • Bengaluru

Hybrid
INR 2,500,000 - 5,200,000
Competitive compensation with bonuses
Hybrid work at Bangalore Innovation Cn
Health, dental, wellness insurance
+3
Ai Ml Engineer
Ai Ml Engineer

Rodic Consultants Pvt Ltd • New Delhi

On-site
INR 1,500,000 - 3,000,000
Data Scientist (AI & ML)
Data Scientist (AI & ML)

National e-Governance Division • New Delhi

On-site
INR 1,500,000 - 2,100,000
AI Developer
AI Developer

Salvo Software • Bengaluru

On-site
INR 1,800,000 - 3,000,000
LLM Model Developer
LLM Model Developer

Accenture PLC • Hyderabad

On-site
INR 1,200,000 - 1,800,000
Full stack Developer (AI)
Full stack Developer (AI)

Digital India Corporation • Delhi

On-site
INR 1,800,000 - 3,200,000
Staff LLM Engineer — Foundation Models
Staff LLM Engineer — Foundation Models

EduRankAI • Kolkata

On-site
INR 2,600,000 - 4,200,000