Design, develop, and implement robust pipelines for building intelligent agents leveraging frameworks such as LangChain and LangGraph.
Collaborate with cross-functional teams to understand complex business problems and translate them into scalable agent-driven solutions utilizing LLMs.
Engineer high-quality prompts for language models, optimizing context efficiency and enhancing model performance.
Develop, test, and deploy scalable applications integrating cutting-edge libraries such as Hugging Face, OpenAI APIs, Reflexion, and Pinecone vector databases.
Pre-process, tokenize, embed, and integrate structured/unstructured data to build dynamic model ecosystems.
Evaluate and optimize the performance of language models and integrate best practices for reasoning frameworks (e.g., Chain of Thought reasoning).
Establish CI/CD pipelines to ensure efficient, reliable deployment of agent systems.
Stay up to date on the latest advancements in LLMs, multi-agent systems, and NLP techniques, and integrate them into workflows.
Create comprehensive documentation detailing architecture, pipelines, and models deployed, ensuring knowledge sharing across teams.
Break down technical concepts and present findings clearly to diverse audiences including non-technical stakeholders.
Required Qualifications
Education:
Ph.D. in a quantitative discipline such as software engineering, machine learning, computer science, or related field. OR an equivalent educational background with an M.S. and 3+ years or B.S. and 5+ years of experience developing AI/ML solutions.
Technical Experience:
Proven experience applying ML, NLP, and Generative AI (GenAI) technologies with both structured and unstructured data.
Expertise in developing agent workflows and applications using libraries like LangChain, LangGraph, and tools such as Reflexion or Pinecone.
Strong programming skills, particularly in Python (additional experience with Rust or JavaScript is a plus), and experience with deep learning frameworks like PyTorch, Jax, or ONNX.
Demonstrated success in end-to-end machine learning lifecycle: POC development, model training, operationalization, scaling, and deployment.
Experience in setting up CI/CD pipelines using tools like Docker, Kubernetes, Helm, Jenkins, or GitHub Actions.
Familiarity with machine learning platforms such as AWS SageMaker, Databricks, or Dataiku for deploying models and building pipelines.
Accomplished developer of visualization tools using libraries like Matplotlib, Seaborn, or Plotly.
Experience optimizing transformer models and scaling LLM-based systems for production applications.
Skills & Attributes:
Ability to design, develop, and deploy machine learning models and autonomous agents from scratch.
Excellent problem-solving skills with a strong foundation in mathematical modeling, machine learning, and debugging complex workflows.
Proven ability to work both independently and collaboratively to deliver impactful results in dynamic environments.
Expertise in explaining technical concepts and presenting insights to diverse business audiences.
Preferred Qualifications
Success in applying ML and AI methods to solve real-world problems across industries, particularly in commercial or enterprise contexts.
Experience managing competing priorities and delivering results in a fast-paced, matrixed environment.
Cross-functional experience working with teams such as product managers, designers, and engineers.
Familiarity with reasoning techniques like Chain of Thought (CoT), Retrieval-Augmented Generation (RAG), or OpenAI Plugin systems is a big plus.
Experience contributing to machine learning libraries like transformers or developing innovative tools for LLM integration.
Background in research environments or academic studies incorporating agent systems is highly desirable.