Bilel SAID
Software Freelancer | Machine learning expert
Phone:
(+49) 1590 6390679
Email:
Location:
Ingolstadt, Germany
​
Age:
33 years old
​
Hello! I'm Bilel
A coding poet driven by the quote "Do it with passion or not at all".
A lifelong learner having a strong techy background and an entrepreneurial vision.
Whether you are facing the challenge to write a clean and optimized code for an embedded target with limited resources or you want to make the best out of your unstructured data using deep learning techniques I am here to effectively help you meet your expectations and be a real asset for your business growth.
​
EXPERIENCE
SEP 2020-Ongoing
Product Owner (Contractor)
Full stack Web & Mobile APP development | Website
German freelancing platform that matches between doctors and hospitals
• Brainstormed and defined the core features (functional & non-functional requirements) to address client’s needs
• Put together and managed remotely an international team of 6 members (Scrum master, UI/UX, designer, Frontend, Backend, Android & iOS mobile developer and DevOps engineer)
• Planned and managed the app development following the agile scrum methodology
• Designed the software architecture: databases, functions and system behavior
• Optimized the cloud infrastructure’s costs while maintaining the app’s performance within KPIs
• Established the CI/CD pipeline using containerization (Docker)
• Designed and implemented a machine learning algorithm to optimize the matching function and thus enhance the user-experience
• Held biweekly meetings with the client and daily alignments with the dev-team to ensure costs, time and quality are met ​
Tools: Jira | Confluence | Slack | Miro | Kubernetes | AWS | Amazon S3 | Amazom SES | Git Action | Argo - CD | Terraform | XD | Angular | Node.js | WordPress | PostgreSQL | MongoDB | Visual Paradigm | Python | TensorFlow | Scikit-Learn
MAR 2019-AUG 2020
Lead Software & AI Engineer
Deep Learning based Autonomous Driving (HWP) | Website
Highway Pilot Situation Interpretation using Deep Learning techniques
• Led the collaborative development of a domain classification concept (Highway/City) between different companies: Astech, EFS and Audi
• Designed the logical and detailed architecture of the common training pipeline for domain classification, corridor estimation and lane change manoeuver prediction modules
• Took part in developing the training pipeline and debugging the models training process (CNN, LSTM, FFN)
• Established the embedded realtime inference of the trained models as well as the continuous online learning pipeline on the cloud (AWS lambda)
Tools : Python | Anaconda | TensorFlow 2.0 | Keras| Scikit-Learn | TensorRT | Tensorboard | C++ | ADS2 | ADTF | GIT | Jenkins | Jira | AWS
NOV 2018-AUG 2020
Project Initiator & Technical Lead
Machine learning based Driver Assistance Systems | Website
Turning recognition for crossing assistance system (KAS) performance enhancement
• Analysed KAS system limitations causing False-Positives (false car braking actions)
• Defined a machine learning based concept for FP mitigation and introduced it to Audi’s innovation board
• Managed a team of 5 persons to achieve a POC for improving KAS behavior
• Achieved a 75% reduction of KAS false actions rate
​
Tools: Python | Anaconda | TensorFlow 1.17 | TensorFlowLib | Bazel | Keras | C++ | Matlab | Scikit-Learn | GIT
OCT 2016-JAN 2019
Embedded Software Developer
Advanced Driver Assistance Systems | Website
Model based development of a safety relevant component for collision mitigation
• Developed model based features conform to MISRA and functional safety norm ISO26262
• Optimized and validated iteratively the time to collision estimator Algorithm
• Introduced and implemented a Continuous Integration concept to the project. This allowed a fully automation of our Build and release process to better meet our biweekly release deadlines
• Project configuration manager: version and sustainability management of all relevant configuration items
• Supported MIL, SIL and functional testing
​
Tools: Matlab | TargetLink | C | PolySpace | Misra | dSPACE | PTC Integrity | Jenkins | DOORS | Python
SEP 2014-SEP 2016
R&D Engineer
Directional Drilling Control System | Website
Robust Control of a Rotary Steering System to automate drilling operations | Certificate
• Modeled and validated the dynamic behavior of a rotary steering system within its operating environment
• Developed a trajectory planning method based on the spline interpolation theory
• Designed a robust control system for efficient path tracking while drilling
• Supervised and coordinated 3 master students involved in the project
• Co-authored a patent: ”Depth-based borehole trajectory control” - USA | Patent
​
Tools: Matlab | Simulink | Stateflow | Acado | TFS | embedded C
MAY 2013-MAY2014
Diploma Thesis
Seismic Image Processing & Pattern Recognition | Website
Put in place an Algorithm to extract the geometry of existing fractures in seismic imaging, reduced the computational costs to the 1/10 and managed to paradigm-shift the company’s standard detection method
​
Tools: Alkemia | Java | C | Matlab | OpenCL | OpenCV
OCT 2012-MAR 2013
Project Thesis
Electrical Vehicle Simulation App - Android | Website
Developed an Android App as a marketing tool to convince car drivers to switch to electrical vehicles by simulating: energy consumption, ROI and the environmental impact
​
Tools: Android Studio | Java | SQLite | Matlab
EDUCATION
2015-PRESENT
Learning, Learning, Learning!!
Continuous learning and certifications
Udacity, Coursera, Haufe Akademie, ...
• Machine & Deep learning certifications. | Certificates
• OOP & embedded software development | Certificates
• Project management & Agile methodology | Certificate
​
2008-2013
Engineering Diploma
Electrical and Computer Engineering
Technical University of Munich, Germany
Automation & Control Systems, Machine learning & Signal processing
Final Grad: GOOD | Diploma
SKILLS
Agile TECH Project Management
From client requirements to delivery
Machine & Deep Learning
TensorFlow, Scikit Learn,Tiny ML, MLOps
Coding
OOP, MBP, Python, embedded C, C++, Matlab
System Design
Solution, Functional & SW-Architecture
Entrepreneurship
Public Speaking
Critical Thinking
TOP PROJECTS
Deep Learning based autonomous driving
- various projects -
Contributed in different challenging deep learning projects to make the era of autonomous driving come closer
• Highway Pilot situation interpretation using a deep learning pipeline enabling real time domain classification, corridors extraction and surrounding drivers intention recognition (TensorRT, TensorFlow, Scikit-learn, AWS lambda, TFRecord, LSTM, CNN)
• Initiator and technical lead of a turning recognition standalone LSTM model to enhance the performance of safety relevant crossing assistance components. Achieved 75 % false positive reduction while keeping the same true positive rate
​
​
Carpooling Mobile APP for north African market
A real-time carpooling app to establish and democratize the sharing economy in north Africa
• Led a customer centered full stack development of the MVP
• Applied machine learning to validate user account using triplet loss function method for image classification and similarity prediction
Munchkin, digital antidepressant for home
Initiator and solution designer of an AI driven platform to assist people with depression after the inpatient stay in the hospital. The concept was the winner of Innovate healthcare Hackathon 2018 in Weiden, Germany (innovation & audience price)
• Implemented a POC in Python using NLP and word embedding for ML based intent recognition and google speech to text API
• Created the Business Model Canvas and pitched the idea for funding in medical valley, Erlangen, Germany
"Proximity tracing" based Coronavirus contagion spread detection
Technical lead of the "AHMI" initiative, a proximity tracing solution that allows immediate recognition of suspicious persons.
• Managed a newly formed 8 volunteers team to work remotely following the Scrum agile method
• Worked on a machine learning based regression model to estimate devices distance based on bluetooth low energy signal strength (TensorflowLite, Scikit-Learn)
Website | Press Article | Facebook Page
​