Sde 2 - Ai/Ml

• Design, build, and deploy end -to -end AI/ML systems with a focus on real -world applications
  
• Develop and optimise LLM -powered applications, including chat systems, copilots, and agent -based workflows
  
• Build scalable APIs and backend systems to serve AI models in production
  
• Work on retrieval -augmented generation (RAG) pipelines and vector search systems
  
• Collaborate with cross -functional teams (product, design, data) to deliver features rapidly
  
• Ensure production readiness through proper testing, monitoring, and optimisation
  
• Mentor junior engineers and contribute to team knowledge sharing
  
• Continuously explore and integrate emerging AI tools, frameworks, and best practices
  

Requirements

• Experience
  
• 2–3 years of experience in AI/ML + Software Engineering roles
  
• Programming & Engineering
  
• Strong proficiency in Python
  
• Understanding of system design
  
• Experience building REST APIs / microservices
  
• MLOps & Infrastructure Experience with:
  
• Docker (containerization)
  
• Kubernetes (deployment & scaling)
  
• CI/CD pipelines for ML systems
  
• Familiarity with cloud platforms (AWS / GCP / Azure)
  
• AI / ML & LLM Stack Hands -on experience with:
  
• LLMs & GenAI Prompt engineering, fine -tuning basics
  
• Frameworks & Libraries like LangChain / LlamaIndex
  
• Hugging Face, PyTorch ecosystem
  
• Retrieval & Search FAISS or other Vector Databases (Pinecone, Weaviate, Chroma, etc.)
  
• Agentic AI Systems, multi -agent workflows, MCP or similar
  
• Preferred Experience
  
• Experience with document parsing & processing pipelines (e.g., PDFs, tables, OCR, structured extraction)
  
• Exposure to knowledge graphs or hybrid retrieval systems
  
• Familiarity with UI frameworks (StreamLit)