Job Description
Generative AI Software Engineer
Are you passionate about building the next generation of intelligent applications? We’re looking for a Generative AI Software Engineer to join our team and help architect and implement AI-powered systems that solve real-world problems using cutting-edge technologies.
You will be responsible to
- Design and implement end-to-end Generative AI solutions using Retrieval-Augmented Generation (RAG) techniques
- Develop and fine-tune AI prompts for various models (OpenAI, Claude, Mistral, etc.)
- Integrate AI models with structured and unstructured data using frameworks like LangChain, LlamaIndex, or similar
- Build scalable, production-grade AI applications using Python, Java, or TypeScript
- Use frameworks like LangChain, LlamaIndex, or similar to orchestrate AI pipelines
- Collaborate with cross-functional teams to deliver intelligent systems that enhance user experience and business capabilities
Qualifications
- Experience developing and deploying RAG-based architectures
- Proficiency with Model Context Protocol (MCP) patterns for dynamic LLM inputs
- Hands-on experience with LangChain, LlamaIndex, Haystack, or related frameworks
- Proficient in Python, Java, or TypeScript
- Strong understanding of prompt engineering and AI reasoning workflows
- Familiarity with vector databases (e.g., Pinecone, FAISS, Weaviate)
- Experience integrating LLMs into real-time or high-performance systems
Desirable
- Knowledge of cloud platforms (AWS/GCP/Azure)
- Experience with LLM fine-tuning or instruction-tuning
- Contributions to open-source GenAI projects
If you are up to the task, send your resume and a short description of your technical leadership experience to [email protected] with the position applied as the subject of the e-mail.
