Role & responsibilities

- AI Architecture: Architect and scale production-grade RAG pipelines, managing everything from document ingestion and advanced chunking strategies to vector database optimization, hybrid search, and multi-model LLM integration.
- Model Integration & Prompting: Integrate leading commercial and open-source LLMs (OpenAI, Anthropic, Meta Llama, etc.) into applications using advanced prompt engineering techniques.
- Application Development: Design, develop, test, and maintain robust software applications based on business and technical requirements.
- Agentic Workflows: Develop multi-agent systems and tools for LLMs to execute complex workflows.
- Code & Quality: Write clean, scalable, and effective code following coding standards and best practices, while performing code reviews to ensure adherence to security and performance standards.
- System Integration: Integrate third-party APIs, databases, and external systems as required.
- Collaboration:



Collaborate with business stakeholders, product teams, and QA teams to understand project requirements and deliver effective solutions.
- Compliance & Security: Ensure applications comply with organizational security, compliance, and data protection standards, particularly regarding sensitive data passed to AI models.

Preferred candidate profile

- Experience with cloud platforms (AWS, Azure, or Google Cloud) and their respective AI services (e.g., Azure OpenAI, AWS Bedrock, GCP Vertex AI).
- Experience with ML Ops and LLM observability tools (e.g., LangSmith, Weights & Biases, MLflow).
- Knowledge of front-end technologies such as HTML, CSS, JavaScript, React, or Angular to build quick AI prototypes.
- Familiarity with Docker, Kubernetes, and CI/CD pipelines

📌 Opening For AI Engineer (Mumbai)
🏢 Valorem Advisors
📍 Mumbai