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

Were looking for a hands-on Data Scientist / Research Scientist who can fine-tune and train open-source LLMs end-to-endnot just run LoRA scripts. Youll 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: youll take models from research experiments evals production.

What Youll 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 Were 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 (90180 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