Agentic Engineer
$135,000–$170,000 year
HybridBoston, Massachusetts, United States
Job Summary
Build and ship production-quality agent capabilities, including tools, retrieval components, memory features, and orchestration steps, within the platform's established architecture using frameworks like LangChain or LangGraph. Integrate RAG, structured tool use, and APIs into enterprise-grade components while extending benchmarking suites to measure agent quality, latency, and safety. Deploy and operate services on AWS infrastructure, instrument token usage and inference costs, and investigate eval regressions or production incidents to land fixes. Ship production code across Go, Python, and React/TypeScript stacks, adhering to security, data isolation, and regulatory compliance standards.
Required Qualifications
- Minimum of 2 days a week onsite in Boston, MA office
- 3–5 years of software engineering experience
- Hands-on work building LLM powered features or agentic systems that reached production users
- Proficiency in Go
- Strong proficiency in a comparable systems language (Rust, TypeScript, Java, C#) with the ability to become productive in Go quickly
- Working knowledge of Python for AI/ML workflows
- Experience building web applications with React (or a comparable modern frontend framework) and TypeScript
- Experience building and shipping LLM-powered applications
- Experience with an agent framework such as LangChain, LangGraph, LlamaIndex, or AutoGen
- Experience directly against model APIs
- Strong engineering fundamentals
- Working understanding of RAG
- Working understanding of embeddings
- Working understanding of vector databases
- Working understanding of prompt/context
- Familiarity with cloud infrastructure, ideally AWS (ECS, Lambda, Bedrock, or comparable services)
- Strong testing and debugging discipline
- The habit of instrumenting what you ship
- Clear written and verbal communication
- A demonstrated appetite for feedback and growth
Desired Qualifications
- Exposure to AI evaluation and observability tooling such as LangSmith, Langfuse, Arize, or Weights & Biases
- Experience with MCP-style tool protocols or building tools for AI agents
- Experience operating services in production (on-call, incident response, performance tuning)
- Familiarity with fine-tuning or post-training techniques (LoRA, PEFT, RLHF, DPO)
- Contributions to open-source AI or agent tooling
- Cybersecurity domain familiarity
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.