Senior Software Engineer

Accordion•Boston, MA

6h•$110,000 - $200,000•Hybrid

About The Position

This posting covers two levels: Associate Software Engineer and Senior Software Engineer. We’re looking for engineers who want to build real agentic systems, not tinker with demos. You’ll work under the direction of Staff-level engineers on live client engagements — writing the agent logic, the RAG pipeline, the eval harness — and growing steadily toward owning a workstream yourself. This is a highly technical, hands-on role in a high-velocity, client-facing environment: sprints are short, client expectations are high, and the work is real from week one. You’ll be expected to ship fast, learn quickly, and raise your own bar on what AI-assisted delivery looks like. The people who thrive here are those who find the pace energizing, not exhausting, and are comfortable being early in their AI-native career while still moving at a fast clip. They treat AI tools as something to get genuinely good at using, communicate clearly with non-technical stakeholders, and course-correct quickly when something isn’t working.

Requirements

Solid Python and/or TypeScript/React fundamentals — you write clean code and can reason about what a framework is doing underneath it
Some hands-on exposure to LLM application development: RAG, tool use, prompt engineering, or agent orchestration (production experience preferred; strong coursework/side-project depth considered for Associate level)
Genuine use of AI coding tools (Claude Code, Cursor, or similar) in your own workflow — you should be able to talk concretely about where they speed you up
Comfort with ambiguity and a fast pace — you won’t always get a clean spec, and that’s the job
Willingness and ability to learn quickly in a client-facing, consulting-style environment

Nice To Haves

Any finance/PE domain exposure — FP&A, GL data, ERP systems (NetSuite, SAP)
Familiarity with LangChain/LangGraph, AutoGen, DSPy, or similar orchestration frameworks
Public work you can point to: a GitHub repo, a side project, a blog post — anything that shows how you think about building
Any prior internship, co-op, or junior role with client- or user-facing exposure

Responsibilities

Build and ship components of multi-agent systems and RAG pipelines for PE-backed portfolio company engagements, under the guidance of more senior engineers
Contribute to prompt engineering, tool design, and deployment for production AI systems
Write and run evals as part of eval-driven development — define success criteria before you build, not after
Help translate client requirements into technical tasks, with support from your pod on the ambiguous parts
Build observability into the systems you ship so quality is measurable, not assumed
At the Senior level: independently own a workstream (an agentic pipeline, a RAG system, or an eval framework) end-to-end, and present your own architecture decisions to internal and client stakeholders