Statement of account · Benjamin AbensurEPFL · Lausanne · 2024 → 2028

BenjaminAbensur

I build software end to end and ship it, I teach two first-year courses, and I take on things outside engineering when they are worth doing.

Portrait of Benjamin AbensurOpen · Summer 2027 internship
Fig. 0 — Benjamin Abensur, Lausanne
  • FieldBSc in Communication Systems (IC)
  • SchoolEPFL, Lausanne
  • Expected graduationJan 2028
  • NowAI Engineer (part-time) at Biosynex · Teaching Assistant at EPFL
  • Looking forSoftware engineering or applied ML, Summer 2027
  • LanguagesFrench (native), English (fluent), Hebrew (basic), Spanish (basic)

Selected work

Five projects, one number each.

Every figure on this page is on my CV, visible in the live app or measured in the public repo, and holds up in an interview.

  1. 01

    ReCHor

    Java 22 · JavaFX 21 · EPFL CS-108, in a pair

    A desktop journey planner for the Swiss public-transport network. It finds every Pareto-optimal journey between two Swiss stops (Connection Scan Algorithm) over real CFF timetables (~258 MB), trading arrival time against changes, by scanning the day's connections once in reverse chronological order over memory-mapped, bit-packed timetable storage that is never deserialised. JavaFX UI with accent-insensitive autocomplete, journey details, iCalendar and GeoJSON export, the search kept off the UI thread; 44 classes, ~3,600 lines of tests, 160 JUnit tests.

    • journey planner
    • open source
    github.com/Benabens/ReCHor
    2.75 Mconnections in one weekday of the real CFF timetables, scanned in a single pass per query. ~258 MB of timetables for seven days, read from memory-mapped files.
    Genève07:35Lausanne08:17Bern09:31Zürich HB10:28Chur11:52St. Moritz13:56
    1. IC 107:35 Genève → 10:28 Zürich HB
    2. IC 310:38 Zürich HB → 11:52 Chur
    3. IR 3811:58 Chur → 13:56 St. Moritz
    Fig. 1Genève → St. Moritz, 28 May 2025: the first journey after 07:00, found by ReCHor's own router on the real CFF timetable, replayed stop by stop.
    ReCHor: Genève to St. Moritz on 28.05.2025 at 07:30; on the left the journeys of the day, on the right the 7h35 journey with its three trains, IC 1, IC 3 and IR 38, every intermediate stop and both changes.
    Fig. 2The app itself on the same query: the day's journeys on the left; on the right the 7h35, IC 1, IC 3 and IR 38 over the Albula line, every stop and both changes.
  2. 02

    Kairo

    Next.js · TypeScript · Python · PostgreSQL (Supabase, row-level security) · GitHub Actions · Railway · Vercel

    An internship search and application platform, live with public users since October 2026. A scheduled Python pipeline on Railway pulls openings from employers' public job feeds and ATS APIs, deduplicates them, then an LLM worker scores each one against every user's profile. Multi-tenant Postgres isolated by row-level security; an application copilot drafts each form answer with its source and flags uncertain ones for the user to check before submitting; 160+ tests, CI. The referral finder turns freeform notes into structured contacts with LLM extraction, then links every opening to the user's direct and indirect connections at that company, so no warm intro is missed.

    • internship platform
    • live since Oct 2026
    kairocareer.app Private code
    0–100the score every opening gets against each user's profile, with the reason for it in one line.
    Kairo landing page: a metal ball on a rail across a dark green scene, an opening card above it, Optiver Quant Intern, Amsterdam, Summer 2027, scored 93, and the line Kairo finds internships that match your profile and helps you prepare your applications.
    Fig. 3The landing, kairocareer.app: Kairo finds the internships that match your profile and helps you prepare your applications.
    Kairo inbox, in French: internships grouped by score band, Excellent 90+ then Very good 80–89, each row with its score, the company, a one-line reason, the deadline and the actions Ignore, Wishlist, Apply.
    Fig. 4Inside the app (in French, on its demo data): the inbox, every opening scored 0–100 against the profile, with the reason in one line and the deadline.
    Kairo offer page: LLM Research Intern at Mistral AI, Paris, scored 96 out of 100, Excellent, with why this score, the requirements that match the profile, the deadline and the next steps: log the outcome, tailor my CV to this offer, prepare the interview, find a contact.
    Fig. 5One offer opened: the score and why, each requirement checked against the profile with the posting's sentence behind it, and the next steps.
    Kairo application section, for a made-up applicant: two fields left for the user, a start date and a certification box to tick themselves; the other answers drafted, one marked pre-filled from your local profile, an availability answer marked To check and a motivation answer marked Draft to review.
    Fig. 6The application copilot: each answer drafted with its source, the uncertain ones flagged, and what only the user can fill left to them. Nothing is sent by the app.
    Kairo, Paths: who can open a door at Mistral AI. A first-degree contact met at a hackathon, with the evidence for the link, then a Research Scientist from the same school with no proven link yet, each with a button to draft a message.
    Fig. 7The referral finder: who can open a door at a company, a direct contact with the proof of the link, then the indirect ones, here someone from the same school.
  3. 03

    Cortex

    Next.js · TypeScript · PostgreSQL · Drizzle · LaTeX · Railway

    An exam-preparation platform. It learns each course's exam format from past papers, weights every topic by how heavily it was examined, schedules spaced revision on weak points, and generates faithful practice exams via a multi-pass LLM pipeline; I used it to prepare my own exams in 3 EPFL courses. Per-user Postgres schemas and cost caps; open to sign-ups since October 2026.

    • exam preparation
    • live
    • open source
    cortexexam.com github.com/Benabens/cortex
    330+tests. Answers accepted only if verified by sandboxed code execution or symbolic checks.
    Cortex landing page: the headline Your shortcut to exam day over folders of blue-lit glass on black, with a Get started with Cortex button.
    Fig. 8The landing, cortexexam.com. Below, the app itself.
    Cortex home, in French, for Introduction to Machine Learning: work on now, Gradient Descent & Optimization, fell once at the finals, 16% of the questions, never practised, with a Train button; then three more topics with how often each fell and their weight.
    Fig. 9Inside the app (in French): the home screen, the topic that pays off most today, weighted by how often it fell at past finals.
    Cortex, Exams page: the exam composer with 16 multiple-choice and 3 open questions, the format detected from the real final, 180 minutes and 116 points, and two ready mock exams marked 16 multiple-choice questions verified.
    Fig. 10The exam composer: the real final's format, detected from past papers, becomes the default, and each ready exam says how many of its answers were verified.
    Cortex, Revision page: coverage of the past finals by topic in course order, 56 multiple-choice and 74 open questions, each topic with its lecture, its question count and its share.
    Fig. 11Revision: every past-final question filed by topic, in course order, with each topic's share of the exams.
  4. 04

    Gaming Addiction Prediction

    Python · NumPy, no ML libraries · EPFL CS-233, team of 3

    Predicted gaming-addiction level (3 classes) and score (0–10) from gaming and mental-health data with KNN, logistic/linear regression, K-Means and an MLP with hand-written backpropagation, every gradient checked against finite differences; two written reports. The point is what accuracy hides: the first MLP scored 85% while never once predicting the rare class, 3% of the data. Inverse-frequency weighted cross-entropy lifted rarest-class recall from 0 to 0.69 and macro-F1 from 0.55 to 0.76 (test set), for 0.75 points of accuracy.

    0 → 0.69rarest-class recall, lifted by an inverse-frequency weighted cross-entropy. Macro-⁠F1 from 0.55 to 0.76 (test set).
    Before: sigmoid + MSE
    LowMediumHighRecall
    Low2661400.95
    Medium327500.70
    High01300.00
    After: softmax + weighted cross-entropy
    LowMediumHighRecall
    Low2582200.92
    Medium317150.66
    High0490.69

    Rows: true class. Columns: predicted class. Shade: share of the true class.

    Fig. 12Test-set confusion matrices, redrawn from the milestone-2 report (400 samples). The baseline never predicts High; the weighted loss recovers 9 of 13.
  5. 05

    ICoop

    Java · PlayEngine (course engine) · EPFL CS-107, in a pair

    A two-player cooperative 2D game on the course's engine: a fire-and-water co-op game with a boss fight, in the spirit of Fireboy and Watergirl. Each player passes what the other cannot; every interaction between players, projectiles, enemies and elemental walls goes through double dispatch (visitor pattern), and each cell decides what can walk or fly over it. Four areas, keys, orbs, bombs, a chest added beyond the brief, and a final boss with ranged attacks and a conditional weak spot. ~3,700 lines.

    • co-op game
    • open source
    github.com/Benabens/ICoop
    ~3,700lines of game code, in 24 actor classes and 4 areas, written on top of an unmodified course engine.
    ICoop, the Spawn area: the fire player and the water player below a manor, with a heart, a bomb and a pressure plate.
    Fig. 13ICoop, the Spawn area: the fire and water players, a bomb to push and a pressure plate.
    ICoop, the OrbWay area: two corridors with hearts and pressure plates, a fire wall and a water wall, one player in each corridor.
    Fig. 14OrbWay: each player clears the wall the other cannot cross.
    ICoop, the Maze: two columns of flaming skulls with health bars, streams of lava and water, both players attacking between them.
    Fig. 15The Maze: the HellSkull gauntlet, lava and water streams, both players mid-swing.

Also on the books

Smaller lines, still real.

Journey

Eight entries, so far.

  1. 01Around 13

    Where it began

    Self-taught Blender, Photoshop and Premiere Pro. 3D artwork and branding for YouTube creators.

  2. 022024

    EPFL

    Bachelor of Science in Communication Systems, School of Computer and Communication Sciences (IC), Lausanne; expected graduation Jan 2028. Introduction to Machine Learning 5.75/6, Algorithms I 5.5/6, Linear Algebra 5.5/6.

  3. 03Jun – Sep 2024

    NanoSynex

    Software Engineer, ML & Statistical Modeling, remote, for a Technion medtech spin-off. Modeled bacterial growth in Python and NumPy to compare Wald's sequential probability ratio test (SPRT) with a fixed-threshold rule for antibiotic susceptibility testing: in simulation, the SPRT reached a decision 20% sooner, with a major-error rate below 3%. Benchmarked the rapid antibiotic test against a veterinary reference laboratory for a validation study, merging both result sets by sample ID in pandas and quantifying agreement rates. Deployed two offline LLMs behind a model router with shared memory, so confidential R&D and investor documents never left the machine, and automated inbox triage with an LLM classifier routing email into custom priority categories (investors, grants, R&D).

  4. 042025

    BABOO, three club nights

    Founder & event producer, Lausanne. Produced 3 club nights end to end that brought in CHF 10,000, one at Noche Club with an internationally touring DJ.

  5. 05Jul 2025

    Scout summer camp, co-camp director

    Mévouillon, France. Co-directed a one-month camp for 80 children from two local groups (Nice, Strasbourg); led a team of 15 counsellors, promoted team leads and wrote the camp's full educational project. Co-managed the €80k camp budget, running the €18k food line myself (local farmers, Intermarché), and built the site at pre-camp: tents, dry toilets, wooden tables.

  6. 06Nov 2025

    Linear Algebra Bootcamp (MATH-111)

    Co-instructor: gave the lectures and wrote the exercise sets of a paid one-week bootcamp for 30 first-year students (mid-semester break).

  7. 07Sep 2026

    Teaching at EPFL

    Teaching assistant for Mechanics (PHYS-101) and Linear Algebra (MATH-111). Selected on academic merit for a Mechanics course of 1,000+ students (CS, Chemistry, EE); I lead a weekly 2-hour exercise session and answer questions on the course's Ed forum.

  8. 08Oct 2026

    Biosynex, AI Engineer

    AI Engineer (part-time), remote, for a Euronext-listed rapid diagnostics company. Building a RAG-based copilot over regulatory and quality documentation to speed up compliance and document search; deploying AI agents and automation pipelines (tender responses, reporting, recurring tasks) and leading AI adoption through training on LLMs, agentic workflows and automation.

Contact

Let's talk about summer 2027.

abensur.benjamin@gmail.com