Of­f­re 61 sur 105 du 05/10/2020, 13:13


Tech­ni­sche Uni­ver­sität Ber­lin - Fac­ulty IV - Insti­tute for Soft­ware Engin­eer­ing and The­or­et­ical Com­puter Sci­ence / Chair Machine Learn­ing

Rese­arch Assist­ant - salary grade E 13 TV-L Ber­liner Hoch­schu­len

under the reserve that funds are gran­ted - part-time employ­ment may be pos­sible

The Ber­lin Insti­tute for the Found­a­tions of Learn­ing and Data (BIFOLD) at the TU Ber­lin (Prof. Klaus Robert Mueller) is look­ing for a sci­ent­ist for an agil­ity pro­ject in the field of machine learn­ing and bioin­form­at­ics. The AP is car­ried out in close cooper­a­tion with the "Evol­u­tion­ary and Can­cer Gen­om­ics" group of Dr. Roland Schwarz, at the Max Del­brück Cen­ter, Ber­lin Insti­tute for Med­ical Sys­tems Bio­logy (MDC-BIMSB).
The Schwarz group devel­ops algorithms for invest­ig­at­ing intrat­umoral het­ero­gen­eity and can­cer evol­u­tion. Based on algorithms for the recon­struc­tion of can­cer evol­u­tion in the patient from somatic copy num­ber aber­ra­tions (SCNAs), a method for assign­ing SCNAs to indi­vidual par­ental hap­lo­types was recently developed and applied. The aim of this pro­ject is the devel­op­ment of a new algorithm for hap­lo­type-spe­cific copy num­ber vari­ants and hap­lo­typ­ing of germline vari­ants using machine learn­ing meth­ods.

Work­ing field:

We are look­ing for an enthu­si­astic and inde­pend­ent researcher in the field of machine learn­ing and bioin­form­at­ics. To model sequen­tial bio­lo­gical data prob­ab­il­istic approaches that can model depend­en­cies between ran­dom vari­ables (e.g. Prob­ab­il­istic Graphic Mod­els) are sug­ges­ted as a start­ing frame­work. Altern­at­ive approaches should be eval­u­ated inde­pend­ently. One focus will be on the con­crete mod­el­ing of bio­lo­gical prop­er­ties and the imple­ment­a­tion of effi­cient algorithms for infer­ence on large amounts of data.


  • Suc­cess­fully com­pleteted stud­ies (Mas­ter, Dip­lom or equi­val­ent; doc­tor­ate desir­able but not required) in math­em­at­ics, phys­ics, com­puter sci­ence or bioin­form­at­ics
  • Extens­ive exper­i­ence in the field of stat­ist­ical meth­ods and machine learn­ing is expec­ted; prior exper­i­ence with Prob­ab­il­istic Graph­ical Mod­els, Hid­den Markov Mod­els or Bayesian net­works is desired
  • Very good pro­gram­ming skills in Python, NumPy / SciPy, PyT­orch / Tensor­Flow are essen­tial
  • Very good lan­guage skills in Eng­lish and Ger­man required
  • Exper­i­ence in ana­lyz­ing gen­omic data and / or sequen­cing data is an advant­age.


How to ap­ply:

Please send your applic­a­tion with the ref­er­ence num­ber and the usual doc­u­ments only via email (single pdf file, max. 5 MB) to

By sub­mit­ting your applic­a­tion via email you con­sent to hav­ing your data elec­tron­ic­ally pro­cessed and saved. Please note that we do not provide a guar­anty for the pro­tec­tion of your per­sonal data when sub­mit­ted as unpro­tec­ted file. Please find our data pro­tec­tion notice acc. DSGVO (Gen­eral Data Pro­tec­tion Reg­u­la­tion) at the TU staff depart­ment homepage: or quick access 214041.

To ensure equal oppor­tun­it­ies between women and men, applic­a­tions by women with the required qual­i­fic­a­tions are expli­citly desired. Qual­i­fied indi­vidu­als with dis­ab­il­it­ies will be favored. The TU Ber­lin val­ues the diversity of its mem­bers and is com­mit­ted to the goals of equal oppor­tun­it­ies.

Tech­nis­che Uni­versität Ber­lin - Der Präsid­ent -
Fak­ultät IV, Insti­tut für Soft­ware­tech­nik und The­or­et­ische Inform­atik,
FG Maschinelles Lernen, Prof. Dr. Müller, Sekr. MAR 4-1, March­str. 23, 10587 Ber­lin