AI Platform Engineer – Multi-Agent & LLM Systems

Repligen

Waltham (MA)

On-site

USD 130,000 - 160,000

Full time

2 days ago

Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Paid time off

Health/dental/vision insurance

Retirement benefits

Flexible spending accounts

Equity potential

Job summary

Repligen seeks an AI Engineer to accelerate enterprise-wide AI adoption. You will design reusable components and patterns for the platform, guiding teams on building AI capabilities with governance and reliability.

This role sits at the data platform heart, shaping how teams deploy AI across the organization. You will work on multi-agent AI, prompt engineering, RAG pipelines, vector search, and API/microservice development to deliver scalable AI across cloud environments.

Qualifications

Bachelor’s degree in Computer Science or related field.
3+ years of experience with AI technologies, particularly GenAI, LLM, Agentic AI, or MLOps, and delivering enterprise-scale, production-grade solutions.
Hands-on experience in building agentic AI systems, including multi-agent workflows, orchestration, and tool integration using frameworks such as AutoGen or CrewAI and failure handling.
Experience deploying and scaling AI solutions on platforms including Azure AI Foundry, Copilot Studio, or Google Vertex AI.
Hands-on experience in machine learning and deep learning frameworks such as TensorFlow, PyTorch, and scikit-learn.
Expertise in GenAI and LLM application development using OpenAI and Anthropic APIs, including advanced prompt engineering and optimization, Retrieval-Augmented Generation architectures, embeddings and vector search, and experience with vector databases.

Responsibilities

Build and orchestrate multi-agent AI systems enabling collaboration on task planning, data retrieval, and execution across complex workflows.
Implement and refine prompt engineering strategies, including prompt chaining, evaluation, and guardrails for accuracy and reliability.
Build and maintain RAG pipelines: data ingestion/indexing, embedding generation, retrieval optimization, grounding and validation.
Develop scalable backend services using Python for data processing.
Design and manage embedding pipelines and vector search infrastructure using Pinecone, FAISS, Weaviate, Databricks or Snowflake.
Integrate LLM capabilities from platforms like OpenAI, Anthropic, and Microsoft into enterprise apps.
Build and maintain scalable APIs and microservices to expose AI capabilities across systems.
Collaborate with data engineering and platform teams to ensure reliable data pipelines and access to high-quality data sources.
Deploy, monitor, and optimize AI solutions in cloud environments (Azure, AWS, GCP) with focus on performance and cost efficiency.
Implement evaluation frameworks and monitoring for LLM outputs, including quality metrics, drift detection, and feedback loops.
Troubleshoot and resolve issues in distributed AI systems for high availability.
Partner with business stakeholders to translate requirements into AI-driven solutions and automation opportunities.
Document architecture and best practices to support scalability and team adoption.