Senior Machine Learning Engineer

Company Description MomentText is a team of engineers and designers focused on building inventive solutions that challenge conventional norms. The company emphasizes continual experimentation with emerging technologies and techniques to stay at the leading edge of its field. Team members are encouraged to apply critical thinking, question assumptions, and push beyond established boundaries. MomentText aims to discover innovative ways to improve and transform traditional industries, offering a dynamic environment for individuals who enjoy solving complex problems.
Role Description
We are looking for a Generative AI / Agentic AI Engineer with 2+ years of hands-on
experience building and deploying production-grade GenAI applications with total ML experience of more than 5 years.
Key Responsibilities
• Design and develop GenAI, Agentic AI, and multi-agent applications for production environments.
• Build end-to-end RAG pipelines, including document ingestion, chunking, embeddings, vector search, hybrid retrieval, reranking, context generation, and LLM response generation.
• Design and implement Graph RAG / Knowledge Graph-based retrieval solutions.
• Build multi-agent workflows with agent orchestration, tool/API calling, state management, memory, retries, guardrails, and human-in-the-loop controls.
• Optimize GenAI applications for latency, scalability, reliability, and cost using techniques such as semantic caching, prompt/response caching, retrieval caching, parallel execution, model routing, and token optimization.
• Implement evaluation, monitoring, tracing, and observability for LLM and agent workflows.
Required Skills
• 2+ years of experience building GenAI / LLM applications with total ML experience of more than 5 years.
• Strong hands-on experience with RAG, Agentic AI, and multi-agent architectures.
• Experience taking GenAI applications from POC to production.
• Strong Python skills and experience with frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, or similar.
• Experience with vector databases/search platforms and LLM APIs such as OpenAI, Azure OpenAI, Anthropic, Gemini, or open-source LLMs.
• Good understanding of LLM evaluation, hallucination reduction, guardrails, observability, performance optimization, and cost optimization.
We are looking for engineers who understand not just GenAI frameworks, but how to build
scalable, reliable, secure, and production-ready AI systems.

Work arrangement
No