Senior Data Scientist

Location: Bengaluru

Description
Job Title
Senior Data Scientist— LLM Training & Fine-tuning (Indian Languages, Tool Calling, Speed)

Location:

Bangalore

About the Role

We’re looking for a hands-on  Data Scientist / Research Scientist  who can  fine-tune and train open-source LLMs end-to-end —not just run LoRA scripts. You’ll own model improvement for  Indian languages + code-switching (Hinglish, etc.) ,  instruction following , and  reliable tool/function calling , with a strong focus on  latency, throughput, and production deployability .
This is a builder role: you’ll take models from research → experiments → evals → production.

What You’ll Do (Responsibilities)

• Train and fine-tune open LLMs  (continued pretraining, SFT, preference optimization like DPO/IPO/ORPO, reward modeling if needed) for:
Indian languages + multilingual / code-switching
Strong instruction following
Reliable tool/function calling (structured JSON, function schemas, deterministic outputs)

• Build  data pipelines  for high-quality training corpora:
Instruction datasets, tool-call traces, multilingual data, synthetic data generation
De-duplication, contamination control, quality filtering, safety filtering

• Develop  evaluation frameworks  and dashboards:
Offline + online evals, regression testing
Tool-calling accuracy, format validity, multilingual benchmarks, latency/cost metrics

• Optimize models for  speed and serving :
Quantization (AWQ/GPTQ/bnb), distillation, speculative decoding, KV-cache optimizations
Serve via vLLM/TGI/Tensor

RT-LLM/ONNX where appropriate

• Improve  alignment and reliability :
Reduce hallucinations, improve refusal behavior, enforce structured outputs
Prompting + training strategies for robust compliance and guardrails

• Collaborate with engineering to ship:
Model packaging, CI for evals, A/B testing, monitoring drift and quality

• Contribute research:
Read papers, propose experiments, publish internal notes, and turn ideas into measurable gains

What We’re Looking For (Qualifications)

Must-Have

• 4 - 6 years  in ML/DS, with  direct LLM training/fine-tuning experience

• Demonstrated ability to run  end-to-end model improvement :
data → training → eval → deployment constraints → iteration

• Strong practical knowledge of:
Transformers, tokenization, multilingual modeling
Fine-tuning methods :
LoRA/QLoRA, full fine-tune, continued pretraining
Alignment : SFT, DPO/IPO/ORPO (and when to use what)

• Experience building or improving  tool/function calling  and structured output reliability

• Strong coding skills in  Python , deep familiarity with  Py Torch

• Comfortable with  distributed training  and GPU stacks:
Deep Speed / FSDP, Accelerate, multi-GPU/multi-node workflows

• Solid ML fundamentals: optimization, regularization, scaling laws intuition, error analysis

Nice-to-Have

• Experience with  Indian language NLP :
Indic scripts, transliteration, normalization, code-mixing, ASR/TTS text quirks

• Experience with  pretraining from scratch  or large-scale continued pretraining

• Practical knowledge of  serving : vLLM / TGI / Tensor

RT-LLM, quantization + calibration, profiling

• Experience with data governance: privacy, PII redaction, dataset documentation Tech Stack (Typical)
PyTorch, Hugging Face Transformers/Datasets, Accelerate
Deep Speed / FSDP, PEFT (LoRA/QLoRA)
Weights & Biases / MLflow
vLLM / TGI / Tensor

RT-LLM
Ray / Airflow / Spark (optional), Docker/Kubernetes
Vector DB / RAG stack familiarity is a plus

What Success Looks Like (90–180 Days)

• Ship a fine-tuned open model that measurably improves:
Instruction following  and  tool calling correctness
Indic language performance + code-switching robustness
Lower latency / higher throughput  at equal quality

• Stand up a repeatable pipeline:
dataset versioning, training recipes, eval harness, regression gates

• Build a roadmap for next upgrades (distillation, preference tuning, multilingual expansion)