Artificial Intelligence Engineer

Position Summary :

We are looking for a passionate AI Engineer to design and build intelligent wrappers, tools, and integrations that form the cognitive layer of our next-generation SaaS platform. The role involves hands-on work with LLMs (OpenAI, Anthropic, etc.), Retrieval-Augmented Generation (RAG) architectures, and custom AI tool development to create high-performance and context-aware systems.

Youll collaborate closely with product, data, and engineering teams to build scalable AI-driven workflows, ensuring that our users experience the true power of applied intelligence across real-world pharma and enterprise use cases.

Key Responsibilities :

Design & Develop AI Wrappers and Tools :

- Build intelligent wrappers and micro-tools leveraging OpenAI MCP, LangChain, or similar frameworks.

- Create structured prompt templates, tool execution flows, and AI agent orchestration pipelines.

Implement RAG Pipelines :

- Architect and deploy Retrieval-Augmented Generation (RAG) pipelines including document retrieval, embedding generation, and context orchestration.

- Optimize knowledge retrieval and context injection for pharma-related data repositories.

Backend Integration :

- Implement backend logic and APIs (in Python or Node.js) to integrate AI tools seamlessly into the platform.

- Work on tool registration, response caching, and data flow management for real-time AI responses.

Data & Search Intelligence :

- Develop and fine-tune embeddings, vector stores, and similarity search logic using frameworks like Pinecone, Weaviate, or PGVector.

- Collaborate with crawling and data teams to connect AI models with structured and unstructured enterprise datasets.

Collaboration & Deployment :

- Partner with frontend teams to expose AI capabilities via chat interfaces, dashboards, and user workflows.

- Contribute to CI/CD pipelines for AI services and optimize performance in production SaaS environments.

Required Skills & Experience :

- Hands-on experience with OpenAI API, LangChain, MCP, or similar LLM tool frameworks.

- Strong understanding of RAG architectures, vector databases, and prompt engineering.

- Proficiency in backend development using Python (FastAPI, Flask) or Node.js (Express, NestJS).

- Proven ability to design and deploy AI-based tools, assistants, or chatbots for enterprise/SaaS use cases.

- Prior experience in SaaS product development with a focus on AI integrations.

- Strong grasp of data structures, API design, and microservice-based architectures.

Bonus / Nice-to-Have :

- Familiarity with the pharma or life sciences domain, especially in data analysis or knowledge retrieval.

- Understanding of model fine-tuning, embedding generation, and context compression techniques.

- Experience with deployment workflows for AI systems (Docker, Kubernetes, Azure/AWS/GCP).

- Exposure to LLM monitoring, evaluation metrics, and token optimization strategies.

What We Offer :

- Opportunity to work on cutting-edge AI systems powering a global SaaS product.

- A hybrid, innovation-driven environment that encourages experimentation and collaboration.

- Direct exposure to advanced OpenAI ecosystem tools and real-world applications in the pharma domain.

- Competitive compensation and opportunities for growth within a fast-scaling AI organization.