Associate, AI/ML Engineer

Legend Biotech is seeking an Associate, AI/ML Engineer as part of the IT team based in Somerset, NJ.

Role Overview

We are seeking a motivated and curious Associate AI/ML Engineer to join our Data & AI team. In this role, you will help design, build, test, and deploy production-grade Generative AI solutions—leveraging large language models (LLMs), retrieval-augmented generation (RAG), and agentic workflows—along with traditional machine learning models that support business and product goals. This is an excellent opportunity for early-career professionals to gain hands-on experience in building safe, reliable AI applications in real-world environments.

Key Responsibilities

• Build and iterate on LLM-powered features (e.g., chat, summarization, extraction, classification) using approved model providers and internal platforms.
• Design retrieval-augmented generation (RAG) solutions, including document ingestion, chunking, embeddings, vector search, and prompt templates.
• Develop and evaluate prompts, tools, and agentic workflows; implement guardrails (grounding, citations, refusal behavior) and improve reliability.
• Create offline and online evaluation for GenAI systems (test sets, automated metrics, human review processes) and track quality over time.
• Assist with developing, training, and evaluating traditional ML models when needed (e.g., classification, regression, anomaly detection, recommendation).
• Clean, preprocess, and analyze structured and unstructured data; build reproducible data pipelines for model inputs and evaluation.
• Collaborate with data scientists, software engineers, security, and product teams to translate business requirements into safe, scalable solutions.
• Support deployment, monitoring, and cost/performance optimization for GenAI services (latency, token usage, caching, drift, incident response).
• Write clean, maintainable, and well-documented code; contribute to code reviews, runbooks, and user documentation.
• Works under guidance to make day-to-day technical decisions such as selecting baseline prompts/RAG patterns, defining evaluation criteria (quality, safety, latency, cost), and proposing experiment plans.
• Escalates architecture, production rollout, security, and data governance decisions to senior engineers/tech lead; contributes input through code reviews, documentation, and demos.

Requirements

• Bachelor’s degree in Computer Science, Data Science, Engineering, Mathematics, or a related field (or equivalent practical experience).
• Internship, academic project, or capstone experience building GenAI/LLM or ML applications.
• Hands-on experience with at least one LLM framework/tooling (e.g., LangChain, LlamaIndex, Semantic Kernel) or equivalent custom orchestration.
• Exposure to RAG building blocks (document ingestion, chunking, embeddings, vector databases/search).
• Familiarity with evaluation approaches for LLM systems (golden sets, qualitative rubrics, automated checks) and basic experiment tracking.
• Familiarity with SQL and relational databases; experience working with unstructured text data is a plus.
• Basic knowledge of cloud platforms (AWS, Azure, or GCP) and deploying services via APIs.
• Experience with version control tools (Git/GitHub) and collaborative development workflows.
• IT Skills: Python; Jupyter/VS Code; Git; Linux fundamentals; Docker basics; REST APIs; SQL; basic CI/CD concepts; familiarity with LLM APIs and orchestration frameworks (e.g., LangChain/LlamaIndex/Semantic Kernel); embeddings and vector databases/search (e.g., Pinecone/FAISS/Azure AI Search or equivalent); experiment tracking/evaluation tooling (e.g., MLflow or equivalent); basic monitoring/observability concepts (logs, traces, latency, token usage).

#Li-BG1

#Li-Hybrid