GenAI & ML Systems Scientist — Production-Ready

Doist; Wilmington (MA); On-site; USD 175,000 - 216,000; Full time

Job summary

TraceLink in Wilmington, MA is hiring an Applied Scientist to design and deploy production-grade GenAI and ML systems. You will build, iterate, and ship multi-agent architectures in the cloud, focusing on LLM/SLM optimization and agent coordination.

You will implement tooling for context engineering, retrieval, and observability, tune models for production use, and collaborate with platform engineers to ensure scalable, secure deployments with monitoring and CI/CD.

Qualifications

• Hands-on design and deployment of production-grade GenAI and ML systems.
• Experience with multi-agent architectures and agent coordination in cloud environments.
• Strong ability to translate ambiguous requirements into concrete architectures and deliverables.

Responsibilities

• Owns end-to-end building and shipping of multi-agent systems (planner/executor, tool-using agents, supervisor patterns).
• Write production-quality code for agent orchestration, memory design and context management.
• Lead context engineering strategies for multi-agent coordination: prompts, state persistence and grounding.
• Fine-tune and deploy SLM models for production use: data creation, training workflows, evaluation, inference serving.
• Build Advanced RAG pipelines end-to-end including semantic search and embeddings.
• Develop evaluation frameworks for latency, cost, robustness and failure mode detection.
• Collaborate with platform/product engineering for scalable, secure deployments with monitoring and CI/CD.

Skills

Multi-agent systems design

LLM/SLM optimization

Inference optimization

Python programming

Cloud & CI/CD

Observability

Context engineering

Education

MS/PhD in CS/ML/NLP/Stats

Tools

Python

AWS/Azure/GCP

Vector DBs

Semantic search

RAG pipelines

Job description

TraceLink in Wilmington, MA is hiring an Applied Scientist to design and deploy production-grade GenAI and ML systems. You will build, iterate, and ship multi-agent architectures in the cloud, focusing on LLM/SLM optimization and agent coordination.

You will implement tooling for context engineering, retrieval, and observability, tune models for production use, and collaborate with platform engineers to ensure scalable, secure deployments with monitoring and CI/CD.