3 days ago
Base Salary
$124k - $168k/yr
Responsibilities
- Develop the agent loop, harness, control flow, subagents, long-running tasks, checkpointing, and recovery mechanisms.
- Design context engineering, memory, state persistence, retrieval, compaction, and summarization strategies for coherent long-running agent execution.
- Design model-facing tools and MCP servers for instrument orchestration, scheduling, data capture, GitHub, repositories, workflows, and developer tooling.
- Implement permissions, sandboxing, approval gates, auditability, data isolation, and defenses against prompt injection and untrusted content.
- Evaluate agents on real multi-step tasks, inspect traces, identify root causes, and improve reliability, tool-use accuracy, cost, and latency.
- Maintain the team's AI-native development harness, including project memory, skills, hooks, MCP, and CI checks.
- Set up reliable agent architecture and infrastructure, and manage configuration, environments, and secrets.
- Build services and interfaces in Python, Node.js/TypeScript, and React, including streaming output and extension points.
- Measure AI-driven engineering workflow throughput, defect rate, and review cost, and coach teammates on AI-native practices.
Requirements
- Around 10 years of software engineering experience, including hands-on experience building and shipping LLM-powered agents in production.
- Experience shipping at least one production agent supporting multi-step tool use, error recovery, and long-running tasks.
- Experience with context engineering, memory, retrieval, RAG, vector indexes, reranking, and measuring coherence or retrieval quality.
- Experience implementing agent permissions, sandboxing, human approval gates, prompt-injection defenses, and audit logging against adversarial inputs.
- Experience designing 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, Node.js/TypeScript, React, streaming output, monitoring, tracing, configuration, and secrets.
- Ability to use autonomous coding agents such as Cursor, Claude Code, Codex, or equivalent as a primary development workflow.
- Experience with agent frameworks such as LangGraph or custom agent harnesses is preferred.
- Working knowledge of Databricks and BI tools such as Sigma, Power BI, or Spotfire is preferred.
- Fine-tuning, prompt optimization, model evaluation, and experience authoring skills, hooks, or MCP servers are preferred.
- A degree or higher education in Computer Science, Engineering, or a related technical field is ideal but not stated as required.
- Interest in life sciences, laboratory instrumentation, or automation is preferred.
Benefits
- Medical, dental, vision, and other insurance benefits.
- Health spending accounts and 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 for US exempt employees.
- Remote-friendly work environment.
- Base pay is listed as $124,000–$168,000 USD, with certain positions potentially eligible for variable pay.
- The posting states that compensation may vary by skills, qualifications, experience, and location, and that candidates with more or less experience are welcome to discuss different levels with a recruiter.
Tech Stack
Categories
About Dotmatics
Dotmatics builds cloud-based R&D scientific software that unifies biology, chemistry, and data management workflows for biopharma, chemicals/materials companies, and academic labs; products include Luma, ELN, GraphPad Prism, Geneious, SnapGene, Protein Metrics, and LabArchives. The company sells SaaS and enterprise licenses for data integration, analysis, and decision support, is headquartered in Boston, and operates as a Siemens company following its acquisition.