Description

You will design, build, and deploy production-grade Generative AI and LLM-based systems, owning the full lifecycle from architecture to monitoring.

This role is on-site.

Responsibilities

• Develop and optimize LLM applications using RAG, prompt engineering, tool use, and structured output design.
• Build and refine retrieval pipelines leveraging vector databases like Pinecone, Weaviate, or FAISS.
• Implement orchestration frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
• Deploy scalable AI services using Docker, Kubernetes, and CI/CD practices on AWS, GCP, or Azure.
• Create evaluation, testing, and monitoring systems to ensure reliability and performance of AI models.

Required Skills

• 8+ years of software engineering or applied AI experience, with 2+ years focused on Generative AI/LLMs in production.
• Strong Python programming and backend/API development skills.
• Hands-on experience with LLM application development, including prompt engineering and RAG optimization.
• Proficiency with orchestration frameworks: LangChain, LlamaIndex, or Semantic Kernel.
• Experience with vector databases and retrieval systems (Pinecone, Weaviate, Chroma, FAISS, Elasticsearch, or Azure AI Search).
• Cloud platform expertise: AWS, GCP, or Azure.
• Knowledge of containerization (Docker, Kubernetes) and CI/CD pipelines.
• Understanding of software architecture, scalability, and distributed systems.
• Bachelor’s degree in Computer Science, Engineering, Machine Learning, or related field.

Preferred Skills

• Experience fine-tuning open-source LLMs or advanced knowledge of NLP for text generation.
• Familiarity with PyTorch, TensorFlow, JAX, or MLOps tools like MLflow, SageMaker, or Vertex AI.
• Experience with AI safety, guardrails, red-teaming, or building multi-agent systems.

Key Skills

Education

Any Graduate