Generative AI / Machine Learning Engineer – LLM, RAG & AI Agents

The position is offered by Square One Resources for a project focused on developing advanced AI solutions such as chatbots, voicebots, AI agents, and Talk-to-Data systems. The role involves the design and implementation of end-to-end Generative AI solutions including RAG pipelines and LLM integration, along with pre-sales activities and technical architecture contributions.

• Strong experience in Machine Learning and Generative AI, particularly with large language models (LLMs), NLP, or multimodal models.
• Good understanding of Deep Learning concepts.
• Strong Python programming skills and knowledge of object-oriented programming.
• Working knowledge of SQL and vector databases.
• Hands-on experience with Azure or Google Cloud Platform.
• Practical knowledge of PyTorch, NumPy, Hugging Face, LangChain, and LangGraph.
• Experience integrating OpenAI or Gemini APIs.
• Proven experience designing and implementing RAG solutions.
• Hands-on experience with MCP servers and clients for LLM-based agents.
• Experience with microservice architectures and AI application deployment.
• Ability to translate business needs into technical solutions.
• Strong analytical, problem-solving, and communication skills.

Nice to have:

• Experience with Databricks.
• Commercial experience delivering Generative AI, NLP, or Computer Vision projects.
• Experience with multimodal AI and production-grade AI agents.
• Experience in technical consulting or pre-sales.
• Ability to mentor and guide junior engineers.

• Design and develop end-to-end Generative AI applications including chatbots, voicebots, and AI agents.
• Build and optimize retrieval-augmented generation (RAG) pipelines involving vector databases, hybrid search, reranking, and retrieval evaluation.
• Develop LLM-based solutions using LangChain, LangGraph, and LlamaIndex.
• Select, fine-tune, and optimize large language models using techniques such as LoRA, QLoRA, and SFT.
• Implement LLM integrations with external tools, APIs, and data sources using Model Context Protocol (MCP).
• Develop and evaluate prompting strategies, guardrails, and model performance.
• Translate business requirements into technical solutions and define project success metrics.
• Support AI solution deployment and project delivery.
• Contribute to technical architecture and pre-sales activities.
• Provide technical guidance and support to junior team members.