Abu Bakar Siddik

Co-founder & Lead AI Engineer

Co-founding and leading AI engineering at an early-stage legal tech venture. Building agentic AI software for lawyers, covering retrieval over case law and contracts and multi-step legal reasoning workflows.

• Design agent workflows that automate legal research, drafting, and review
• Own the AI architecture: retrieval, agent orchestration, evaluation, and production deployment
• Set the technical direction of the product and the engineering team

AI Consultant

AI consulting for an education platform serving Bangladeshi students.

• Designed AI learning systems for the Bangladeshi curriculum
• Advised on LLM integration, curriculum design, and responsible AI adoption

Applied AI Engineer (L-2)

Led the Core RAG & AI Team, owning the architecture of a production RAG platform: retrieval, agent orchestration, evaluation, and a provider layer with no vendor lock-in.

• Scaled the platform from 100 to 10,000+ concurrent users at ChatGPT-level latency, without vendor lock-in
• Reduced hallucinations by 98% via hybrid search, reranking, citation extraction, and strict source-grounding
• Designed multi-agent workflows with explicit state management, improving system throughput by 30%
• Built agentic RAG with multi-layer memory (short-term, long-term, semantic) and time-aware retrieval, lifting contextual accuracy by 45%
• Implemented a citation system with cross-source referencing across documents, web sources, and memory layers
• Optimized chat hot paths via prepare-then-query pre-computation, parallelized resolution, and fewer database round-trips, reducing end-to-end latency
• Built persistent user memory end-to-end: extraction service, schemas, CRUD APIs, and chat-flow integration
• Refactored the LLM provider/model layer into modular configs and rolled out new model tiers behind feature flags
• Built an internal evaluation benchmark and RAG suite management tooling, cutting evaluation time by 99%
• Built image generation and editing pipelines with pixel-level control, integrated into agent workflows as first-class tools
• Migrated the backend to async SQLAlchemy and restructured conversation, message-source, and repository layers for scale

Machine Learning Engineer

Joined as Trainee Engineer and promoted to ML Engineer (L-1) after 4 months. Built production-grade LLM integrations and private AI deployments for enterprise clients.

• Designed Port and Adapter (Hexagonal) architecture for multi-provider LLM integration (OpenAI, Anthropic, local LLMs)
• Deployed LLM evaluation pipeline with source-based fact-checking, improving response reliability by 35%
• Reduced jailbreak and safety risk by 45% with layered guardrails and prompt hardening
• Delivered private on-premise AI solution for enterprise client, air-gapped, reducing cloud dependency and latency by ~30%
• Used Docker and self-hosted GPU infrastructure, cutting model startup time by 20–25%
• Built full RAG application (3M+ sample database) using open-source LLMs, Next.js, LangChain, and FastAPI as Trainee

ML Researcher & Engineer

Joined as intern, progressed to Researcher & Engineer. Built conversational AI systems and contributed to Bengali language NLP research.

• Built Rasa-based chatbots for financial services and mobile operator industries (PoC and pilot deployments)
• Developed multilingual restaurant chatbot supporting English, Banglish, and Bangla natural language inputs
• Collaborated on Bengali Automatic Speech Recognition (ASR) tool
• Researched Voice Activity Detection (VAD) technologies to improve system efficiency and responsiveness
• Served as Data Annotation Team Lead, managing NLP dataset collection, labeling, and quality assurance

Data Science Apprentice

Early-career data science role working on OCR, text summarization, data visualization, and analytical reporting across client projects.

• Evaluated and compared OCR libraries, contributing to a real-world document processing tool
• Researched and applied modern text summarization algorithms to real-world client data
• Built custom Google Data Studio dashboards for client data communication and stakeholder reporting
• Pre-processed and cleaned complex datasets, designed interactive dashboards, and performed web scraping

Technical Secretary → IT Manager → Executive Member

5 years 3 months of progressive leadership in RUET's robotics and engineering society. Grew from Executive Member to Technical Secretary, organizing technical events and managing digital infrastructure.

• Technical Secretary (Nov 2023 – May 2024): Led technical initiatives and workshop programs for the society
• IT Manager (Dec 2022 – Nov 2023): Managed society's digital infrastructure, website, and technical operations
• Executive Member (Mar 2019 – Dec 2022): Contributed to robotics competitions, events, and member activities

Rajshahi University of Engineering & Technology (RUET)

Graduate research on agent security and alignment, done part-time alongside engineering work.

Research

Agent security and LLM alignment

Supervisor

Dr. Md. Rabiul Islam

Thesis

Alignment drift in language models after domain-specific fine-tuning (in progress)

• Thesis studies how narrow fine-tuning can shift a model's behaviour outside its target domain, and which mitigations hold
• Published a review of cyber-capable AI agents on arXiv (2026): vulnerabilities, evaluation containment, and defensive response
• Building Jontro, a replayable tool-use dataset for Bangla-language agents

Rajshahi University of Engineering & Technology (RUET)

An engineering degree spanning control systems, robotics, signal processing, and programming, which became the base for later work in machine learning.

Thesis

Deep learning for medical applications

Coursework

Artificial Intelligence · Machine Learning Algorithms · Software Engineering · Robotics · Numerical Analysis & Statistics · Digital Signal Processing & Machine Vision · Automation

• Three applied machine learning papers (2023–2024), on genetic-disorder classification, detecting AI-generated images, and patient monitoring
• Competed in ML challenges, including Mayo Clinic STRIP AI on Kaggle and a top 0.5% finish in Analytics Vidhya's Dataverse Hack