Blue Machines.ai - Senior Data Scientist - LLM Training & Fine-tuning job opportunity at Apna.



Date2025-12-30T11:02:12.476Z bot
Apna Blue Machines.ai - Senior Data Scientist - LLM Training & Fine-tuning
Experience: 6-years
Pattern: full-time
apply Apply Now
Salary:
Status:

Job

Copy Link Report
degreeGeneral
loacation Bengaluru, India
loacation Bengaluru....India

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

Other Ai Matches

key Account Manager - Mumbai Applicants are expected to have a solid experience in handling Job related tasks
Business Development Executive Applicants are expected to have a solid experience in handling Job related tasks
IT Support Engineer Applicants are expected to have a solid experience in handling Job related tasks
Admission Counsellor - Apna Advantage (Noida) Applicants are expected to have a solid experience in handling Job related tasks
Business Development Executive (B2B - Field sales) - Bangalore Applicants are expected to have a solid experience in handling Job related tasks
Business Development Manager Applicants are expected to have a solid experience in handling Job related tasks
Business Development Manager- Field Sales | Delhi NCR Applicants are expected to have a solid experience in handling Job related tasks
Business Development Manager - Enterprise | Consultant POD | Kolkata Applicants are expected to have a solid experience in handling Job related tasks
Business Development Manager - | Consultant POD | Mumbai Applicants are expected to have a solid experience in handling Job related tasks
Senior Sales Manager (Chennai) - BlueMachines.ai Applicants are expected to have a solid experience in handling Job related tasks
Admission Counsellor - Noida & Bangalore (WFO) Applicants are expected to have a solid experience in handling Job related tasks
Inside Sales Associate (Hindi and English Fluency is Must ) Work From Office Applicants are expected to have a solid experience in handling Job related tasks
Lead Product Manager - AI Products, Marketplace Applicants are expected to have a solid experience in handling Marketplace related tasks
Business Development Executive Chandigarh Applicants are expected to have a solid experience in handling Job related tasks
Business Development Manager - Lucknow Applicants are expected to have a solid experience in handling Job related tasks
Admission Counsellor - Apna Advantage (Fresher- Bangalore) Applicants are expected to have a solid experience in handling Job related tasks
HR Business Partner (HRBP) Applicants are expected to have a solid experience in handling Job related tasks
Business Development Executive - B2B Field sales | Gurgaon Applicants are expected to have a solid experience in handling Job related tasks
Admission Counsellor Noida Applicants are expected to have a solid experience in handling Job related tasks
Sales Operation Executive Applicants are expected to have a solid experience in handling Job related tasks
Business Development Executive (B2B-Field Sales) North Applicants are expected to have a solid experience in handling Job related tasks
Director - Human Resource, Job Marketplace Applicants are expected to have a solid experience in handling Job Marketplace related tasks
Sales Development Representative - Bangalore Applicants are expected to have a solid experience in handling Job related tasks