Job Title

Job DescriptionJob TitleSenior Data Scientist— LLM Training & Fine-tuning (Indian Languages, Tool Calling, Speed)Location: BangaloreAbout the RoleWe’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-switchingStrong instruction followingReliable 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 generationDe-duplication, contamination control, quality filtering, safety filtering• Develop evaluation frameworks and dashboards:Offline + online evals, regression testingTool-calling accuracy, format validity, multilingual benchmarks, latency/cost metrics• Optimize models for speed and serving:Quantization (AWQ/GPTQ/bnb), distillation, speculative decoding, KV-cache optimizationsServe via vLLM/TGI/TensorRT-LLM/ONNX where appropriate• Improve alignment and reliability:Reduce hallucinations, improve refusal behavior, enforce structured outputsPrompting + 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 gainsWhat 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 modelingFine-tuning methods: LoRA/QLoRA, full fine-tune, continued pretrainingAlignment: 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 analysisNice-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 documentationTech Stack (Typical)PyTorch, Hugging Face Transformers/Datasets, AccelerateDeepSpeed / FSDP, PEFT (LoRA/QLoRA)Weights & Biases / MLflowvLLM / TGI / TensorRT-LLMRay / Airflow / Spark (optional), Docker/KubernetesVector DB / RAG stack familiarity is a plusWhat Success Looks Like (90–180 Days)• Ship a fine-tuned open model that measurably improves:Instruction following and tool calling correctnessIndic language performance + code-switching robustnessLower 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)