AI Engineer I

Repligen Corporation is expanding enterprise-scale AI adoption, and this role helps turn AI strategy into reusable platform components. You will design governance-in-code capabilities and deliver data and AI platform deployment that supports reliable, production-grade AI across the organization. Based in Waltham, MA (onsite), this position offers an annual salary range of USD 130,000 to 160,000.

What you’ll be building

• Build and orchestrate multi-agent AI systems using state-of-the-art platforms so agents can collaborate on planning, data retrieval, and execution across complex workflows.
• Develop and continuously improve prompt engineering strategies, including prompt chaining, evaluation, and guardrails to raise accuracy and reliability.
• Create and maintain RAG pipelines, covering data ingestion and indexing, embedding generation, retrieval optimization, and response grounding and validation.
• Develop scalable backend services in Python for data processing, supporting dependable delivery of AI capabilities.
• Design and run embedding pipelines and vector search infrastructure using tools such as Pinecone, FAISS, Weaviate, Databricks, or Snowflake.
• Integrate LLM capabilities from OpenAI, Anthropic, and Microsoft into enterprise applications.
• Build and maintain APIs and microservices to expose AI functionality across systems and applications.
• Deploy, monitor, and optimize AI solutions in Azure, AWS, and GCP, focusing on performance, scalability, and cost efficiency.
• Implement evaluation and monitoring for LLM outputs, including quality metrics, drift detection, and feedback loops.
• Troubleshoot distributed AI issues to maintain high availability and reliability.
• Partner with business stakeholders to translate requirements into AI-driven solutions and automation opportunities.
• Document architecture, design decisions, and best practices to support scalability and team adoption.

Required qualifications

• Bachelor’s degree in computer science, Statistics, Data Science, Information Systems, or a related field.
• 3+ years of experience with AI technologies, particularly GenAI, LLM, Agentic AI, or MLOps, delivering enterprise-scale, production-grade solutions.
• Hands-on experience building agentic AI systems, including multi-agent workflows, orchestration, and tool integration using frameworks such as AutoGen or CrewAI, with failure handling.
• Experience deploying and scaling AI solutions on Azure AI Foundry, Copilot Studio, or Google Vertex AI.
• Hands-on experience with machine learning and deep learning frameworks: TensorFlow, PyTorch, and scikit-learn.
• Strong expertise in LLM application development using OpenAI and Anthropic APIs, including advanced prompt engineering and optimization.
• Expertise in RAG architectures, including embeddings, semantic search, contextual retrieval strategies, and response grounding.
• Experience with vector databases such as Pinecone, FAISS, or Weaviate, and/or AI data platforms such as Databricks or Snowflake.
• Strong background in API development, microservices architecture, and distributed systems.
• Experience with knowledge graphs, graph databases, or hybrid retrieval systems.
• Proficiency in Python.
• Experience with CI/CD, infrastructure as code (Terraform), monitoring and debugging, and managing AI/ML solutions in AWS, Azure, and GCP.

Compensation and benefits

• Paid time off
• Health/dental/vision
• Retirement benefits and flexible spending accounts
• Employees may be eligible to participate in a variable cash program (bonus or commission)
• Eligible roles may receive equity as part of the compensation package