Software Engineer, Agentic AI

Dotmatics • Boston, MA

22h • $124,000 - $168,000

About The Position

Dotmatics is seeking an experienced Software Engineer to build and own the AI agent at the core of the Dotmatics Luma platform. The role is part of a small, high-trust engineering team working with Product, scientists, and the wider organization. The engineer will own the agent end to end, including its reasoning, tools, memory, failure recovery, and evaluation.

This is an AI-native engineering role. Coding agents are the default path for implementation, while the engineer remains accountable for architecture, correctness, security, testing, review, and production quality. The role involves adapting practices as models improve and shipping reliable production agents rather than demos.

The position also includes building the infrastructure and surrounding services and interfaces for the agent, using Python, Node.js/TypeScript, and React. Dotmatics describes its environment as dynamic, collaborative, global, and remote-friendly. Compensation is based on job-related skills, experience, qualifications, and location; the posted base pay range is $124,000–$168,000 USD. Some positions may also be eligible for variable pay.

Requirements

• Around 10 years of software engineering experience; the posting notes candidates with more or less experience are welcome.
• Hands-on experience building LLM-powered agents in production.
• Use autonomous coding agents such as Cursor, Claude Code, Codex, or equivalent as the primary development approach.
• Have shipped at least one LLM-powered agent to real users that handles multi-step tool use, error recovery, and long-running tasks.
• Experience with context engineering, memory, and retrieval in a long-running LLM application, including explaining context-window contents and compaction and how coherence and retrieval quality were measured.
• Experience implementing and testing agent security, including permissions, sandboxing, human approval gates, prompt-injection defenses, and audit logging.
• Experience building tools or MCP servers for model use and measuring tool-selection and call accuracy.
• Production engineering experience with Python, type checking, automated tests, packaging in CI, and Node.js/TypeScript and React services and interfaces, including streaming output.
• Experience with monitoring, tracing, and managed configuration and secrets.
• A degree or higher education in Computer Science, Engineering, or a related technical field is described as ideal, not mandatory.
• Interest in life sciences, lab instrumentation, or automation is described as ideal.

Nice To Haves

• Experience with agent frameworks such as LangGraph, or with building custom harnesses from scratch.
• Working knowledge of Databricks and BI tools such as Sigma, Power BI, or Spotfire.
• Experience with observability for LLM systems, including tracing and cost and latency monitoring.
• Experience with fine-tuning, prompt optimization, or model evaluation.
• Authored skills, hooks, or MCP servers that made agent-driven delivery repeatable for a team.

Responsibilities

• Develop the agent loop, harness, and control flow connecting the model, tools, and state, including subagents, long-running tasks, checkpointing, and recovery.
• Engineer context by deciding what enters the context window, when to compact or summarize it, and how to maintain coherence over long-running experiments.
• Design agent tools with clear interfaces and descriptions for instrument orchestration, scheduling, data capture, and developer workflows and tools.
• Implement agent memory and state persistence so it can build on earlier work.
• Implement permissions and sandboxing, including boundaries for autonomous actions, human approval, and mistake containment.
• Defend against prompt injection and untrusted content, with auditability and data isolation appropriate for regulated environments.
• Evaluate the agent on real multi-step tasks; analyze traces, identify root causes, and improve the harness, tools, or prompts to improve reliability, tool-use accuracy, cost, and latency.
• Adapt the harness as models improve and remove scaffolding that is no longer needed.
• Run an AI-first development loop by scoping, planning, delegating to coding agents, verifying, and shipping; maintain the team's development agent harness, including project memory, skills, hooks, MCP, and CI checks.
• Measure and improve AI-driven development workflows using throughput, defect rate, and review cost, and coach others on AI-native practices.
• Set up architecture and infrastructure for reliable agent operation, and manage configuration, environments, and secrets.
• Deliver services and interfaces around the agent in Python, Node.js/TypeScript, and React, including streaming output and extension points such as MCP.

Benefits

• Medical, dental, vision, and insurance.
• Health Spending Accounts.
• Wellness benefits, including mental health apps and fitness perks.
• Company-paid life and disability insurance.
• 401(k) retirement plan with a 4% company match and immediate vesting.
• Flexible Time Off Plan for US exempt employees.
• Certain positions may be eligible for variable pay; details are discussed with the recruiter.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed