Python ML/AI Engineer( Itransition )

Описание

Sofi y a P ova rg o
Ph on e : + 3 75 4 4 7 6 4 1 6 4 3
Em ail : s o fiy ap ova rg o @ gm ail.c o m
Lo catio n : M in sk
P ort fo li o : h ttp s:/ /g it h ub .c o m /S o fiy aP o va rg o ?ta b =re p osit o rie s
C O NTA CTABO UT M EAppli e d C om pute r S cie n ce s tu d en t ( Y e ar 2 ) a t t h e F a c u lt y o f A ppli e d M ath em atic s a n d In fo rm atic s,
sp ec ia li z in g in M ac h in e L e arn in g a n d D ata S cie n ce. D eve lo p in g e xp ert is e t h ro ugh h an d s- o n
exp erie n ce in K ag gle c o m petit io ns a n d h ac ka th o ns ( O ZO N t e c h 2 0 25 q uali t y c o ntro l, A I a ss is ta n t).
K ag gle c o ntib uto r.
H ARD S K IL LS M ac h in e L e arn in g
N atu ra l L a n gu age P ro cessin g & L a rg e L a n gu age M od els
D eep L e arn in g
Tim e S erie s
C om pute r V is io n
M ath em atic s
D ata A naly tic s
P yth o n
G it
S Q L
Basic s o f S ta tis tic s, S te p ik , B io in fo rm atic s In stit u te
D ata V is u ali z a tio n, K ag gle
I n tro d uctio n t o D ata S cie n ce a n d M ac h in e L e arn in g, S te p ik , B io in fo rm atic s In stit u te
D eep L e arn in g, D eep L e arn in g S ch o ol, M osc o w In stit u te o f P hysic s a n d T e c h no lo gy ( M IP T)
M ac h in e L e arn in g C ours e , F A M CS B SU
C O URSES Pro gra m min g L a n gu age s:
P yth on
SQ L
C++ ( B asic ): U nd ers ta n d in g o f O OP a n d a lg o rit h m s
Mac h in e L e arn in g & M LO ps:
C la ssic al M L: S cik it - le arn , C atB oost, X G Boost, L ig h tG BM ( fu ll c yc le : f r o m E D A t o m od el
d ep lo y m en t)
H yp erp ara m ete r O ptim iz a tio n : O ptu na, H yp ero p t
M LO ps: M Lflo w , D VC , b asic D ocke r
D eep L e arn in g & C om pute r V is io n :
Fra m ew ork s: P yTo rc h , T e n so rF lo w , K e ra s, T o rc h V is io n
A rc h it e ctu re s: C NNs ( R e sN et, E ffic ie n tN et), b asic u nd ers ta n d in g o f T ra n sfo rm ers f o r C V
N atu ra l L a n gu age P ro cessin g ( N LP ) & L a rg e L a n gu age M od els ( L L M s):
N LP L ib ra rie s: N LT K , S p aC y, H uggin g F a c e t ra n sfo rm ers
L LM s: P ra c tic al e xp erie n ce w it h O pen A I A PI, prompt e n gin eerin g, f in e-tu nin g o f s m alle r m od els
( e .g ., B ER T, D is tilB ER T) f o r t e xt c la ssif ic atio n
R A G B asic s: U nd ers ta n d in g o f t h e R etrieval- A ugm en te d G en era tio n c o ncep t
T E C HNIC AL S K IL LSMach in e L e arn in g E n g in eer/ A I E n g in eer

Data E n gin eerin g & D ata b ase s: P o stg re S Q L, S Q Lit e
D ata V is u ali z a tio n : M atp lo tli b , Seab orn , Plo tly , Plo tly Exp re ss , Stre am li t , Exc el/ G oogle
S heets
V ers io n C on tro l & C olla b ora tio n : G it H ub , G it L a b , G it
W eb F ra m ew ork s : S tre am li t , F a stA PI ( fo r c re atin g M L A PI e n d p oin ts ), T kin te r, A io gra m
M ath em atic al F o und atio n: L in ear A lg e b ra , P ro b ab ili t y & S ta tis tic s, M ath em atic al A naly sis ,
D is c re te M ath em atic s, O ptim iz a tio n M eth o d s, D if fe re n tia l E q uatio ns
La n gu age s:
E n gli s h : B 1- B 2– t e c h nic al d ocu m en ta tio n r e ad in g, c o m munic atio n
R ussia n : N ativ e
P R O JE C TSYo u Tu b e v id eo s u m mary A n a p pli c atio n f o r s u m mariz in g c o nte n t f r o m Y o uTu b e v id eo s a n d w eb sit e s u sin g m od ern A I
te c h no lo gie s.
C re d it S c o rrin gBuild in g a s c o rin g m od el f o r t h e d ata se t h tt p s:/ / w w w.k a g gle .c o m /d ata se ts /la o ts e /c re d it - ris k -
d ata se t a s p art o f t h e M ac h in e le arn in g c o urs e
W ate r P u m pED A a n d b re akd ow n c la ssif ic atio n m od el b ase d o n s e n so r in d ic ato rs ( t im e s e rie s) o f a w ate r
p um p u sin g L S TM
C ar p ric e p re d ic tio n Pars in g d ata se t a n d c le an in g , R e atu re E n gin eerin g, E D A , M od el M APE ( 5 % )M usic g e n re c la ssif ic atio nap pli c atio n o n S tre am li t f o r d ow nlo ad in g a n d a n aly zin g a u d io f ile s.
M usic g e n re c la ssif ie r m od ule b ase d o n t h e H ugg in gFa c e m od el c la ssif ie s m usic b y g e n re a n d
m ake s r e c o m men d atio ns
A I a ssis ta n t C RM hac ka th o n