AI/ML

Posted on June 10, 2025

Apply Now

Job Description

  • AI/ML / 7-8 yrs
  • Core Technical Skills Required
  • 1. Machine Learning & Deep Learning
  • Supervised & unsupervised learning
  • Time-series modeling (RNNs, LSTMs, Transformers)
  • Classification & regression tasks
  • Multimodal data fusion (combining audio, video, and text)
  • 2. Signal Processing
  • Audio: MFCC, spectrograms, pitch, energy, prosody analysis
  • Video: Facial landmark tracking, pose estimation, gaze detection
  • 3. Computer Vision
  • Face detection & alignment
  • Facial expression recognition (FER)
  • Body language/gesture recognition
  • 4. Natural Language Processing (NLP)
  • Sentiment analysis
  • Emotion classification from text (speech-to-text pipeline)
  • Contextual embedding models (e.g., BERT, RoBERTa)
  • 5. Speech Processing
  • Voice activity detection (VAD)
  • Emotion classification from speech (e.g., anger, calm, joy, fear)
  • Tools: librosa, pyAudioAnalysis, OpenSMILE
  • 6. Data Engineering & Annotation
  • Synchronizing and processing multimodal streams (audio/video/text)
  • Annotation tools for emotion/behavior labeling (e.g., ELAN, Audacity, VIA)
  • Handling large video/audio datasets

Required Skills

1. machine learning & deep learning supervised & unsupervised learning time-series modeling (rnns lstms transformers) classification & regression tasks multimodal data fusion (combining audio video and text) 2. signal processing audio: mfcc spectrograms pitch energy prosody analysis video: facial landmark tracking pose estimation gaze detection