--- title: "ANKUR MISHRA - Machine Learning Researcher in Patna | Tal" description: "Meet ANKUR MISHRA, Student at Rajiv Gandhi Institute of Petroleum Technology (RGIPT)| Asynq | CodingJr based in Patna. AI stack includes claude code, deepmind, and hugging face. Explore public work links including github." image: "https://tal.club/meet/ankur-mishra-4/share-image" --- # ANKUR MISHRA on Tal ## Headline Student at Rajiv Gandhi Institute of Petroleum Technology \(RGIPT\)\| Asynq \| CodingJr ## About I’m a Computer Science engineer focused on LLM inference, model optimization, and AI systems\. My recent work includes: • Implementing Llama\-3\.2\-1B from scratch in PyTorch, including GQA, RoPE, KV cache, SwiGLU and inference optimizations\. • Building GPTQ and AWQ quantization from scratch, including packed INT4 weights and activation\-aware scaling\. • Analyzing inference performance using roofline modeling across T4, L4 and A100 GPUs\. • Worked on LLM fine\-tuning, knowledge distillation, and ML systems during internships at Siemens, Asynq Technologies, and Coding Jr\. I’m particularly interested in LLM inference, quantization, GPU optimization, inference serving, and ML systems\. GitHub: github\.com/ankur110 ## Location Patna ## AI stack claude code deepmind hugging face ollama llama\.cpp vLLM ## Work experience Machine Learning Researcher at Siemens, Mar 2026 \- Jul 2026 · 5 mos, Implemented and benchmarked 7 hybrid physics \+ deep\-learning architectures \(3 Series/Parallel, Caspari 4\-step, PINN, PINNverse, plus 1 novel\) in PyTorch across 2 industrial case studies from 4 papers\. Trained 6 crystallization model variants — 3 architectures × 2 backbones \(681K\-param Transformer, 282K\-param LSTM\) — on 520 simulated runs, reaching R² > 0\.99 on batch dynamics\. Built a 4\-step pipeline \(CasADi/IPOPT → feature selection → 8 MLPs → LSODA rollout\) for a real pharmaceutical reactor \(3 states, 2 inputs, 8 unknown parameters\), hitting R² 0\.9998 / 0\.928 / 0\.9999 on 2 unseen batches\. Traced a non\-identifiability bug inverting feed→temperature response; 1 physics\-motivated input restriction lifted test R² 0\.859 → 0\.924 with zero retraining elsewhere\. Designed a novel end\-to\-end differentiable architecture merging 2 stages into 1 loop \(BPTT through differentiable RK4, physics\-restricted inputs\); filed as a Siemens invention disclosure\. Recovered 5 kinetic parameters from 25 measurements at 10% noise via 8,192 Sobol collocation points; MDMM cut recovery error 13% → 4% and runtime 25 → 20 min\. Reproduced a 6\-agent LLM system \(AutoGen, GPT\-5\) auto\-generating MPC controllers on the BOPTEST benchmark — 340 passing tests, multi\- vs single\-agent success rate compared across repeated runs\. LLM Engineer Intern at Asynq, Jun 2025 \- Aug 2025 · 3 mos, Remote, Architected ML pipelines for 3 client projects, dedicating 60%\+ of resources to the flagship Sales Agent system\. Fine\-tuned Transformer models for spam classification, achieving 95% precision via targeted hyperparameter optimization\. Engineered a deterministic fallback algorithm to handle API failures, ensuring 99\.9% decision logic reliability\. Implemented cosine similarity search for vector retrieval, enabling real\-time updates to embeddings from user feedback\. Designed human\-in\-the\-loop validation loops to capture rejection data, automatically enriching the training dataset\. Optimized inference orchestration using LangGraph, reducing latency by 40% for the Employee Assessment tool\. Machine Learning Engineer at Coding Jr, Jun 2024 \- Aug 2024 · 3 mos, Fine\-tuned 10\+ LLMs \(Mistral, Llama 2\) via QLoRA and PEFT, and curated 10k\+ de\-duplicated instruction samples for robust supervised fine\-tuning \(SFT\)\. Stabilized multi\-GPU training with BF16 mixed precision and gradient accumulation on consumer GPUs; benchmarked SOTA architectures on perplexity and syntax accuracy\. ## Education Bachelor of Technology \- BTech, Cse, Rajiv Gandhi Institute of Petroleum Technology \(RGIPT\) ## Public links - github: https://github\.com/ankur110 [View the original profile](https://tal.club/meet/ankur-mishra-4) ```json { "@context": "https://schema.org", "@graph": [ { "@type": "Person", "@id": "https://tal.club/meet/ankur-mishra-4#person", "name": "ANKUR MISHRA", "url": "https://tal.club/meet/ankur-mishra-4", "image": "https://tal.club/meet/ankur-mishra-4/profile-photo.jpg", "description": "Meet ANKUR MISHRA, Student at Rajiv Gandhi Institute of Petroleum Technology (RGIPT)| Asynq | CodingJr based in Patna. AI stack includes claude code, deepmind, and hugging face. Explore public work links including github.", "jobTitle": "Machine Learning Researcher", "worksFor": { "@type": "Organization", "name": "Siemens" }, "hasOccupation": { "@type": "Occupation", "name": "Machine Learning Researcher" }, "homeLocation": { "@type": "Place", "name": "Patna" }, "alumniOf": [ { "@type": "EducationalOrganization", "name": "Rajiv Gandhi Institute of Petroleum Technology (RGIPT)" } ], "knowsAbout": [ "claude code", "deepmind", "hugging face", "ollama", "llama.cpp", "vLLM" ], "sameAs": [ "https://github.com/ankur110" ], "mainEntityOfPage": { "@id": "https://tal.club/meet/ankur-mishra-4#webpage" } }, { "@type": "ProfilePage", "@id": "https://tal.club/meet/ankur-mishra-4#webpage", "url": "https://tal.club/meet/ankur-mishra-4", "name": "ANKUR MISHRA on Tal", "description": "Meet ANKUR MISHRA, Student at Rajiv Gandhi Institute of Petroleum Technology (RGIPT)| Asynq | CodingJr based in Patna. AI stack includes claude code, deepmind, and hugging face. Explore public work links including github.", "dateModified": "2026-09-09T14:57:26.111Z", "isPartOf": { "@id": "https://tal.club/#website" }, "mainEntity": { "@id": "https://tal.club/meet/ankur-mishra-4#person" }, "primaryImageOfPage": { "@type": "ImageObject", "url": "https://tal.club/meet/ankur-mishra-4/profile-photo.jpg", "contentUrl": "https://tal.club/meet/ankur-mishra-4/profile-photo.jpg", "caption": "ANKUR MISHRA profile photo on Tal" }, "inLanguage": "en-IN" } ] } ```