We are working with an innovative technology company at the forefront of building enterprise-scale AI applications. They are seeking a talented engineer to join their team and contribute to cutting-edge Generative AI and Agentic AI projects, delivering intelligent solutions from concept to deployment.
The Role
- Design, develop, and maintain enterprise AI applications.
- Build scalable Retrieval-Augmented Generation (RAG) solutions using vector databases and embedding models.
- Develop end-to-end document processing pipelines, including parsing, extraction, and semantic retrieval.
- Integrate commercial and open-source Large Language Models (LLMs).
- Build real-time AI applications using Streaming APIs and Server-Sent Events (SSE).
- Design and develop Agentic AI solutions using multi-agent frameworks.
What You'll Need
- 3+ years of experience developing enterprise applications with strong Python, React, and MongoDB skills.
- Hands-on experience with Generative AI (GenAI), Large Language Models (LLMs), RAG, and Vector Databases.
- Experience building document parsing, OCR, extraction, and indexing pipelines.
- Proficiency in integrating LLM APIs from leading providers (OpenAI, Azure OpenAI, Anthropic, Gemini).
- Experience with Streaming APIs, Server-Sent Events (SSE), and Agentic AI solutions.
- Strong experience with REST APIs, Microservices, Git, and Agile/Scrum methodologies.
What's On Offer
- Opportunity to work on cutting-edge Generative AI and Agentic AI projects.
- Collaborate with experienced architects, AI engineers, and product leaders.
- Solve challenging real-world problems using modern AI and cloud technologies.
- Competitive compensation with opportunities for long-term growth.
Apply via Haystack today!