GenAI Engineer

SOFTWARE ENGINEER - GenAI

We're building the next generation of AI systems that think, respond, and solve problems in real time. If you're excited about LLM-powered applications, RAG pipelines, and prompt engineering this role is for you!

Role and Responsibility

• Build scalable RAG systems by developing chunking pipelines, generating embeddings, and implementing hybrid retrieval using ANN (PGVector, Qdrant) and BM25 for structured and unstructured content.
• Design and optimize prompt flows for GPT-class and open-source models, including function-calling, fallback logic, and safety guardrails.
• Drive continuous improvement through A/B testing and real-world feedback loops.
• Design and Deploy LLM chains as production-ready APIs using FastAPI/Flask, while measuring and optimizing for latency, usage cost, and response success.
• Strong proficiency with Python and its standard libraries.
• Experienced in integrating LLM APIs such as OpenAI, Mistral, Anthropic and similar platforms into real-world applications.
• Familiar with LLM orchestration frameworks like LangChain, LlamaIndex, or custom-built solutions.
• Strong working knowledge of version control (Git), containerization (Docker), and CI/CD pipelines for maintaining scalable, production-ready codebases.
• Collaborate with cross-functional teams to ship, monitor, and iterate on GenAI features.