Applied Scientist — GenAI & Multi-Agent ML Systems

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

Job summary

TraceLink in Wilmington, MA is hiring an Applied Scientist to lead the design and deployment of production‑grade GenAI and ML systems with a hands‑on focus on LLM/SLM optimization for agentic, multi‑agent architectures in cloud environments.

This role is ideal for someone with deep expertise in LLM/SLM optimization for agent‑based systems, and hands‑on experience building large‑scale multi‑agent systems in the cloud.

Qualifications

• Context engineering for multi‑agent systems (prompt orchestration, tool calling, memory/state design)
• Fine‑tuning of SLMs and production deployment
• Experience with Advanced RAG, semantic search, embeddings, and cross‑encoders
• Ability to translate ambiguous requirements into concrete architectures and metrics

Responsibilities

• Hands‑on ownership of building and shipping multi‑agent systems from prototype to production
• Write production‑quality code for agent orchestration and memory design
• Lead context engineering strategies for multi‑agent coordination
• Fine‑tune and deploy SLM models for production usage
• Build Advanced RAG pipelines end‑to‑end (semantic search, embeddings, retrieval)
• Implement evaluation frameworks for multi‑agent systems (quality, latency, cost)
• Collaborate with platform/product engineering for cloud‑native, observable solutions
• Optimize for cost and latency (routing, caching, inference)
• Mentor peers through code reviews and architecture sessions

Skills

Context engineering

SLM fine-tuning

RAG and embeddings

Python

Cloud deployment

Education

MS/PhD in CS/ML/NLP/Stats

Tools

AWS/Azure/GCP

Job description

TraceLink in Wilmington, MA is hiring an Applied Scientist to lead the design and deployment of production‑grade GenAI and ML systems with a hands‑on focus on LLM/SLM optimization for agentic, multi‑agent architectures in cloud environments.

This role is ideal for someone with deep expertise in LLM/SLM optimization for agent‑based systems, and hands‑on experience building large‑scale multi‑agent systems in the cloud.