The company is seeking to solve complex problems using advanced AI and ML technologies, particularly focusing on intelligent systems and autonomous agents that can reason, plan, and act.
Requirements
- 8+ years of experience in ML, applied AI, or software engineering roles focused on intelligent systems.
- Hands-on expertise in LLMs (e.g., GPT-4, Claude, PaLM, LLaMA, Mistral) and prompt engineering.
- Proven experience with LangChain, including chains, agents, tools, retrievers, and vector store integrations.
- Strong experience working on Agentic AI systems, including task planning, memory/context management, and goal-driven architectures.
- Deep proficiency in Python, including writing modular, testable, production-ready ML code.
- Practical knowledge of Google Cloud AI tools, such as Vertex AI, AutoML, BigQuery ML, or TFX.
- Experience with vector databases (e.g., FAISS, Pinecone, Weaviate) and RAG pipelines.
Responsibilities
- Design and develop LLM-powered applications and agents that can reason, plan, and act autonomously using Agentic AI frameworks.
- Build complex LangChain-based pipelines, integrating tools, memory, agents, retrievers, and external data sources.
- Leverage Google ADK tools (e.g., Vertex AI, AutoML, TFX) for model training, deployment, and orchestration.
- Implement and optimize retrieval-augmented generation (RAG) pipelines with vector databases and external data integration.
- Create autonomous agents capable of executing multi-step tasks with long-term memory, goal orientation, and tool usage.
- Develop prompt strategies, fine-tuning approaches, and evaluation frameworks for LLM-based agents.
- Collaborate with data scientists, software engineers, and product teams to integrate AI systems into user-facing products.
Other
- Stay current on latest research in LLMs, agentic AI, and autonomous systems, and apply relevant findings to engineering solutions.
