Staff LLM Engineer — Foundation Models

EduRankAI

Kolkata

On-site

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

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

EduRankAI in Kolkata, India, seeks a Staff LLM Training & Serving engineer to own the end-to-end training stack for foundational models from 1B to 70B parameters. You will lead SFT/RLHF/DPO efforts, design robust evaluation harnesses, and drive inference optimizations with the serving team.

You will mentor mid/senior LLM engineers and shape training methodologies across multiple model generations, writing code, debugging, and profiling at 3am as needed.

Qualifications

  • Experience training large transformer models (1B–70B parameters).
  • Strong implementation experience with RLHF and related techniques.
  • Deep knowledge of model evaluation, safety and calibration strategies.
  • Proficiency in modern ML tooling and kernels optimization.

Responsibilities

  • Own the pre-training pipeline for large transformer models.
  • Lead SFT and preference-optimisation runs (RLHF, DPO, KTO, IPO).
  • Design the evaluation harness for reasoning, factuality, and safety.
  • Drive inference optimization with the serving team (KV cache, quantisation, batching).
  • Mentor engineers to reach Staff readiness within 24 months.
  • Publish public technical reports where applicable.

Skills

7B+ params
PyTorch/JAX/CUDA
Distributed training
RLHF/DPO
vLLM/SGLang/TensorRT-LLM
Tokenizer/data pipeline

Tools

FSDP
Megatron
DeepSpeed

Job description

LLM Training & Serving

Own the LLM training stack. Pre-train, supervised fine-tune, RLHF/DPO, evaluation, release. You will lead the recipes that produce EduRankAI's foundation models and you will be the engineer the rest of the platform calls when training stalls at 3am.This is a hands‑on Staff role. You will write code, run trainings, debug NaNs, profile kernels. You will also mentor a small team of mid/senior LLM engineers and shape our training methodology over multiple model generations.

Responsibilities
  • Own the pre-training pipeline for 1B → 70B parameter transformer models.
  • Lead SFT and preference‑optimisation runs (RLHF, DPO, KTO, IPO as the field moves).
  • Design the eval harness — Indic reasoning, factuality, safety, refusal calibration.
  • Drive inference optimisation jointly with the serving team (KV cache, quantisation, batching).
  • Mentor the LLM engineers; bring at least one to Staff readiness over 24 months.
  • Author public technical reports where the work merits it.
Skills
  • Trained 7B+ parameter transformers from scratch
  • PyTorch + JAX + CUDA at depth
  • Distributed training (FSDP / Megatron / DeepSpeed)
  • RLHF / DPO implementation experience
  • vLLM / SGLang / TensorRT-LLM
  • Tokenizer + data pipeline expertise
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Staff Infra Engineer — LLM Serving
Staff Infra Engineer — LLM Serving

EduRankAI • Kolkata District

On-site
INR 4,500,000 - 7,000,000
ML Engineer — Applied
ML Engineer — Applied

EduRankAI • Kolkata District

On-site
INR 900,000 - 1,500,000
LLM Fine Tuning Expert
LLM Fine Tuning Expert

VARTIS Platforms • Mumbai

On-site
INR 4,000,000 - 9,000,000
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
LMTS - Lead AI/ML Engineer (LLM Post-Training)
LMTS - Lead AI/ML Engineer (LLM Post-Training)

Skynett Studio • Bengaluru

Hybrid
INR 3,000,000 - 5,400,000
LLM Finetuning Expert
LLM Finetuning Expert

LenDenClub • Mumbai

On-site
INR 3,000,000 - 5,000,000
Staff ML Engineer — Applied
Staff ML Engineer — Applied

EduRankAI • Kolkata

On-site
INR 1,200,000 - 2,400,000
AI/ML Engineer
AI/ML Engineer

National e-Governance Division • New Delhi

On-site
INR 1,500,000 - 2,100,000
AI Engineer LLM Fine-Tuning & Reasoning Systems
AI Engineer LLM Fine-Tuning & Reasoning Systems

ZySec AI • Hyderabad

On-site
INR 1,200,000 - 2,100,000
Senior Artificial Intelligence Engineer
Senior Artificial Intelligence Engineer

pepcus software services • Indore District, Pune District

On-site
INR 4,000,000 - 7,000,000