Machine learning engineer

Ankit Kumar Singh —
building production ML, one experiment at a time.

ML Software Engineer at Andor Communications. I fine-tune models, build RAG pipelines and AI agents, and ship them into real products used by people — not just notebooks.

training_log.sh
// 01_about

Who I am

I'm a Machine Learning Software Engineer working on Andor Communications' AI product suite, where I fine-tune deep learning models for production use and build the infrastructure — RAG pipelines, LLM fine-tuning, AI agents — that makes them deployable, not just demoable.

My background is in Computer Science and Design from IIIT Delhi, where I spent four years moving between applied ML projects (classification, generative modelling, signal filtering) and the systems work needed to actually run them — databases, evaluation pipelines, CLI tools.

I care most about the gap between a model that works in a paper and one that works in production: calibration, evaluation, latency, and the unglamorous engineering that closes that gap.

education
B.Tech, Computer Science & Design
IIIT Delhi · 2021 – 2025
based in
New Delhi, India
currently
ML Software Engineer @ Andor Communications
focus areas
Fine-tuning · RAG · AI agents · CV
// 02_experience

Experience

Andor Communications Pvt Ltd

Machine Learning Software Engineer
Jan 2025 — Present
  • Fine-tuned and implemented BiRefNet-based deep learning models for background image processing on custom datasets built in-house, optimized for production AI tools.
  • Fine-tuned and optimized Hugging Face models on custom datasets; implemented LLM fine-tuning (LoRA / PEFT), RAG pipelines, argument-driven configurations, and AI agents for automation — with robust evaluation and scalable deployment.
IoU 0.92 SSIM 0.95 LoRA / PEFT RAG pipelines
// 03_projects

Selected projects

Academic and independent work spanning classical ML, generative modelling, and applied systems.

Feb 2024 — May 2024 · team of 2

Breast Cancer Classification

Compared five classical ML models for tumour classification, then used PCA to compress the feature space while preserving almost all of the signal.

scikit-learnpandasseaborn
98.25% accuracy · 67% fewer features · 95.16% variance retained
Aug 2024 — Dec 2024 · team of 3

Autoencoder-Driven Gen AI with Kalman Filter

A lightweight architecture pairing autoencoders with Kalman filters for text classification, sentiment analysis, and sequence modelling on memory- and compute-constrained systems.

PythonKalman filterML
Smaller, faster models — without leaning on LLM-scale compute
Jun 2022 — Aug 2022 · team of 2

Online Pharmacy

Rebuilt a CLI transaction platform end to end, automating invoicing and order workflows on top of a redesigned relational schema.

MySQLDBMS
50+ daily transactions · 70% less manual work · 40% faster queries
// 04_skills

Stack

Languages

C++PythonSQL

Core

DSAOOPStatistical MLDBMSNetworks

Dev tools

GitGitHubPostman

Databases

MySQLMongoDB

Platforms

VS CodeIntelliJArch LinuxKaggle
// 05_achievements

Achievements & leadership

AIR 66 — Meesho
2nd place — ML Challenge, IIT Kanpur
3rd place — Beat the Market, IIT Kanpur
Finalist — NPCI Hackathon, IIT Bombay
Top 10% — NMTC
Qualified — Flipkart GRiD 6.0
Volunteer — Youthsala, IIIT Delhi
Organizer — Astra Fest
Design & Fundraising — Salt n Pepper Club
// 06_contact

Get in touch

Open to ML engineering roles, research collaboration, and interesting problems. Type a message or use the mic to dictate it.

The fastest way to reach me is email — every message from this form opens directly in your mail app, addressed to me.

ankitiit2003@gmail.com
+91 82906 92578
Noida, India
Click the mic to speak your message instead of typing.