Sr. Data Scientist - LLM Training and Fine-tuning

Job 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/TensorRT-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 PyTorch

• Comfortable with distributed training and GPU stacks:

DeepSpeed / 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 / TensorRT-LLM, quantization + calibration, profiling

• Experience with data governance: privacy, PII redaction, dataset documentation

Tech Stack (Typical)

• PyTorch, Hugging Face Transformers/Datasets, Accelerate
• DeepSpeed / FSDP, PEFT (LoRA/QLoRA)
• Weights & Biases / MLflow
• vLLM / TGI / TensorRT-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)

Interview Process

• 30-min intro + role fit
• Technical deep dive: prior LLM work (training/evals/production constraints)
• Take-home or live exercise: design an LLM fine-tuning + eval plan for tool calling + Indic language
• Systems round: training/serving tradeoffs, cost/latency, failure modes
• Culture + collaboration round