Job Description
We are looking for an early-career Agentic AI Engineer to help build and evolve AI-powered systems that automate and improve supply chain workflows. In this role, you’ll work alongside experienced engineers and data scientists to develop agentic AI / GenAI features, integrate knowledge-based retrieval (RAG) patterns, and contribute to testing and validation approaches for AI systems that can behave in non-deterministic ways.
This is a strong opportunity for someone who is eager to grow in both software engineering and applied GenAI, and wants to work on real-world enterprise problems in supply chain and (optionally) life sciences.
Key Responsibilities
- Support the design and implementation of agentic AI / GenAI systems that assist in automating supply chain workflows.
- Build and maintain backend services and integrations using Python and/or Java.
- Contribute to multi-agent workflows, such as tool execution, routing, agent collaboration patterns, and task orchestration.
- Assist in creating testing and validation strategies for AI systems, including evaluation datasets, regression testing, and behavior monitoring.
- Help implement and improve knowledge base systems, including RAG pipelines, grounding strategies, and retrieval quality improvements.
- Contribute to experimentation with:
- lightweight fine-tuning approaches for small language models (SLMs)
- reinforcement-learning-inspired improvement loops for NLP/GenAI tasks (where applicable)
- Partner with product and domain teams to understand supply chain needs and translate them into working software.
- Participate in code reviews, documentation, and operational support to ensure high-quality production systems.
Required Qualifications
- Master’s/Bachelors degree in Data Science, Artificial Intelligence, Machine Learning, Computer Science, or a closely related discipline.
- 0–2 years of professional experience in software engineering, AI engineering, or ML engineering (internships and co-ops count) OR equivalent experience
- Strong programming skills in Python and/or Java, including writing production-quality code.
- Familiarity with cloud platforms such as AWS, GCP, or Azure (academic, personal, or internship experience is acceptable).
- Interest or exposure to Generative AI concepts, such as LLMs, agent workflows, tool calling, or multi-step reasoning.
- Understanding of core engineering fundamentals:
- APIs and services
- basic distributed systems concepts
- debugging and performance basics
- data structures & algorithms
- Ability to learn quickly, take feedback well, and collaborate effectively in a team environment.
Preferred Qualifications
- Coursework, projects, or hands-on experience with agentic or multi-step AI systems, including non-deterministic behavior patterns.
- Exposure to designing knowledge base solutions, such as:
- Retrieval-Augmented Generation (RAG)
- embedding-based search
- hybrid search approaches
- reranking or relevance evaluation
- Experience or academic background in one of the following:
- fine-tuning small language models (SLMs)
- training or adapting NLP models
- Reinforcement learning concepts applied to language systems
- Exposure to event-driven or reactive systems
- Interest in supply chain domains (logistics, manufacturing, procurement, etc.).
- Knowledge of the life sciences supply chain is a plus, but not required.
What Success Looks Like
- You can take a defined task (e.g., building a new RAG retriever, improving evaluation coverage, or implementing a new agent tool) and deliver a working solution with support from senior engineers.
- You write clean, testable code and steadily improve your ability to debug real-world production issues.
- You contribute to AI system reliability through experiments, evaluation improvements, and thoughtful engineering.
Who You Are
- Curious, motivated, and excited to build AI-driven products that ship to real users.
- Comfortable working with a mix of predictable engineering tasks and emerging AI workflows.
- Strong team player with a growth mindset and a willingness to learn.
