New Requirement of Generative AI Expert

Skills Position: Generative AI Expert Location: Chandigarh, India Experience: 3+ Years (LLMs, LangChain, RAG, Vector Databases, Groq) Employment Type: Full-Time Apply at: hr@cogniter.com About the Role Cogniter Technologies is on the lookout for a passionate and experienced Generative AI Expert to join our AI/ML team. If you're skilled in working with large language models (LLMs), LangChain, RAG architecture, and vector databases, and you're excited about building cutting-edge AI applications for real-world impact—this role is for you. You’ll be at the forefront of designing and deploying intelligent systems that integrate advanced AI frameworks and real-time inference technologies into scalable solutions. What You’ll Do Architect and develop intelligent AI applications using leading LLMs like GPT-4, LLaMA, Mistral, or Falcon Build and fine-tune Retrieval-Augmented Generation (RAG) pipelines for high-quality contextual outputs Create modular AI agents using LangChain or equivalent orchestration frameworks Implement semantic search and retrieval using vector databases (e.g., Pinecone, FAISS) Work with real-time inference engines such as Groq for performance-driven deployment Fine-tune models for domain-specific use cases and optimize token usage Stay updated with the latest in NLP, STT/TTS, prompt engineering, and AI toolsets Collaborate closely with cross-functional teams to bring AI features into production environments Required Skills Minimum 3 years of hands-on experience in Generative AI, LLMs, and NLP Proficiency with LangChain , RAG pipelines , and vector search systems Strong command over Python and/or Node.js Experience with LLM fine-tuning and deployment (e.g., GPT-4, LLaMA, Falcon) Deep understanding of NLP concepts, token optimization, and STT/TTS processes Familiarity with AI ecosystems like OpenAI, Hugging Face, and Anthropic Strong analytical and debugging abilities Nice to Have Experience with Groq or similar AI accelerators for real-time inference Knowledge of prompt engineering and reinforcement learning with human feedback (RLHF) Understanding of MLOps workflows and model lifecycle management Exposure to multimodal systems integrating text, images, and voice Why Work with Us? Be part of AI projects that deliver real business value Thrive in a collaborative and research-driven environment Access modern infrastructure, tools, and cloud platforms Play a vital role in developing the future of enterprise AI and automation To Apply: Send your updated resume to hr@cogniter.com. Only shortlisted candidates will be contacted. Apply Now