Senior Machine Learning Engineer (LLMs - Agentic Workflows)

We are seeking a skilled Senior Machine Learning Engineer to join our team, with a specialized focus on agentic workflows. The ideal candidate will have experience designing, developing, and deploying systems that transition LLMs from passive responders to autonomous agents capable of planning, tool-use, and self-correction.

Functional Responsibilities:

Architect how the agent breaks down a complex user request into a series of actionable sub-tasks.

Develop "Plan-and-Execute" or "ReAct" (Reason + Act) patterns where the model thinks before it acts.

Design robust systems to maintain "short-term memory" across long-running tasks, ensuring the agent doesn't lose track of its goal or get stuck in infinite loops.

Create the interface between the LLM and external software, databases, or APIs.

Standardize how the agent calls functions, interacts with legacy systems, or executes Python code in a sandboxed environment.

Implement error-handling and self-correction.

Build custom evaluation frameworks to measure trajectory success—not just whether the final answer was right, but if the steps taken to get there were efficient and safe.

Set up monitoring to visualize the agent's "thought process" and identify exactly where a multi-step workflow broke down.

Ensure the agent doesn't "hallucinate" tool usage or take unintended actions through strict guardrails and Human-in-the-Loop (HITL) checkpoints for high-stakes decisions.

Qualifications:

Bachelor’s or Master’s degree in Computer Science, Statistics, Mathematics, or a related field.

5+ years of hands-on experience developing and deploying machine learning models in production environments.

Strong software engineering fundamentals, including data structures, algorithms, system design, OOP, and API design & integration.

Proven experience designing and implementing agentic architectures, including multi-agent workflows, tool-calling, state management, and human-in-the-loop patterns.

Expertise in integrating Generative AI frameworks and APIs (such as LangChain, LangGraph, OpenAI, and Claude) into production-grade applications.

Strong understanding of LLM fundamentals, systematic prompt engineering (chain-of-thought, few-shot), and debugging tools like LangSmith or Arize Phoenix.

Experience with vector databases (Pinecone, Milvus, Qdrant) for retrieval-augmented generation (RAG) and long-term agent memory.

Experience with cloud platforms such as AWS, GCP, or Azure for deploying AI workloads.