AI Engineer

Develop and Deploy AI Applications: Design, develop, and deploy AI-driven applications utilizing large language models like GPT, Llama, and Claude. Implement and optimize algorithms for natural language processing (NLP) tasks and other AI-related functionalities. Create autonomous and semi-autonomous agents capable of planning, tool-use, and multi-step decision flows. Utilize LangChain/LangGraph: Integrate LangChain and LangGraph to build robust agent workflows, tool orchestration, and memory-backed systems. Implement advanced capabilities like routing, evaluation loops, and agent monitoring. Function Calling and API Integration: Develop and maintain function-calling mechanisms for seamless integration with other services and applications. Create and manage APIs to facilitate communication between AI models and external systems. Python Development: Write clean, efficient, and scalable code in Python for AI and machine learning applications. Use modern Python libraries (Pydantic, async frameworks, orchestration tools) to build reliable systems. GCP Cloud Services: Deploy and manage AI and machine learning applications on Google Cloud Platform (GCP) infrastructure. Utilize GCP services such as Compute Engine, Cloud Storage, Cloud Functions, and Vertex AI for model training, deployment, and storage. Data Science and Machine Learning: Apply core ML and data science methods to improve model performance and system reliability. Build and maintain large-scale scraping and ingestion pipelines using Playwright, BeautifulSoup, etc. Retrieval-Augmented Generation (RAG) Systems: Architect, optimize, and maintain RAG pipelines combining vector stores, embeddings, and hybrid search. Improve retrieval quality, latency, filtering, and contextual relevance. Agentic Systems: Build multi-tool, multi-step agent workflows capable of autonomous reasoning, planning, and execution. Improve agent reliability through evaluation, guardrails, and structured output enforcement. Collaboration and Communication: Collaborate with cross-functional teams to understand requirements and deliver AI solutions. Communicate technical concepts and project progress to stakeholders effectively. Qualifications: Bachelor’s/Master’s degree in CS, Engineering, Data Science, or related fields. 2-7 years of experience in AI/ML, with strong exposure to LLMs and agent frameworks. Strong Python skills; experience with LangChain, LangGraph, Pydantic, and async tooling. Hands-on GCP experience, including deploying production AI workloads. Understanding of ML fundamentals, embeddings, vector databases, and retrieval systems. Experience with function calling, API integrations, and RAG pipelines. Strong problem-solving skills and attention to detail. Ability to work independently and in collaborative environments. Preferred Skills: Familiarity with multi-modal models and fine-tuning methods (LoRA, adapters). Knowledge of MLOps and model monitoring practices. Experience with containerization (Docker, Kubernetes). Strong documentation, experimentation, and evaluation skills. Experience with scraping frameworks like Playwright. Building or utilizing ontologies with AI systems. Experience with Databricks. Understanding of finance related concepts.