Research Engineer, Agents
Research Engineers at Distyl build and productionize reliable agentic AI systems and compound architectures for enterprise workflows. They design agents, develop evaluation frameworks, run experiments on reasoning and failure modes, and integrate into customer environments.
About the job
Key Responsibilities
- Design, prototype, and implement agentic AI systems that perform reliably across complex enterprise workflows
- Build compound AI architectures that combine planning, tool use, retrieval, memory, evaluation, orchestration, and execution
- Investigate how agents reason, coordinate, recover from errors, and interact with external systems under real-world constraints
- Develop evaluation frameworks that measure agent behavior, task completion, reliability, robustness, and failure modes
- Create tools and abstractions that make agent behavior easier to observe, debug, test, and improve
- Partner with AI Researchers to explore new agent architectures and with AI Engineers to harden successful approaches for production use
- Integrate agents into customer APIs, applications, data platforms, and operational workflows
- Communicate clearly with internal teams and customer stakeholders about agent capabilities, limitations, tradeoffs, and risks
Requirements
- Experience building agentic AI systems that use models, tools, retrieval, planning, memory, or multi-step execution to complete real tasks
- Strong engineering fundamentals: clean, maintainable Python and debugging complex, stateful systems
- Systems-level reasoning about how prompts, tools, context, evaluators, state, orchestration, and external APIs interact
- Research-oriented builder: curious about why agents succeed or fail; design experiments to test architectures and behaviors
- AI-native working style: use AI tools daily to write code, debug, explore designs, analyze traces, and accelerate experimentation
- Bias towards showing vs. telling: prefer working demonstrations, traces, evaluations, and production behavior
- Comfort in customer environments: translate ambiguous business workflows into concrete agent designs and explain system behavior to stakeholders
- Ownership mentality: responsibility for whether an agentic system performs reliably, safely, and usefully in production
Compensation and Benefits
- Base salary range: $150000 – $250000, depending on experience, location, and level
- Meaningful equity
- 100% covered medical, dental, and vision for employees and dependents
- 401(k) with additional perks (e.g., commuter benefits, in‑office lunch)
- Access to state‑of‑the‑art models, generous usage of modern AI tools, and real‑world business problems
- Ownership of high‑impact projects across top enterprises
- Mission‑driven, fast‑moving culture that prizes curiosity, pragmatism, and excellence
Skills
Python, Agentic Ai Systems, Compound Ai Architectures, Planning, Tool Use, Retrieval, Memory, Evaluation Frameworks, Orchestration, Multi-Step Execution, Prompt Engineering, Debugging, Experiment Design
Similar jobs
ML Engineering jobs
LangChain
New York, NYBuild and teach reliable AI agent systems through customer workshops, technical content, guidance, and reference implementations. The role requires strong Python and agent-development experience plus a background delivering customer-facing technical training.
Roboflow
San Francisco, CA
Build reinforcement-learning environments, evaluations, datasets, and scalable infrastructure for frontier AI capabilities. The role suits a high-agency generalist engineer with experience in agents, evaluations, or RL workflows and strong communication skills.
Beacon Biosignals
Boston, MADevelop and productionize machine- and deep-learning algorithms for biosignal and EEG data used in medical devices, clinical development, and diagnostics. The role requires 4+ years of industry experience, DSP and statistics expertise, PyTorch proficiency, and familiarity with regulated environments and production ML practices.
Applied Intuition
Sunnyvale, CA
Develop and deploy ML-first behavior prediction and planning systems for autonomous vehicles, forecasting the motion and interactions of road users. Requires a bachelor's degree, deep learning lifecycle expertise, and at least three years of production software experience with C++ or Python.
Fab2
Austin, TXBuild the AI platform behind fab2, including model infrastructure, agent systems, evaluations, and tools for engineering and fab operations. The role requires strong production software engineering skills and comfort working across frontend, backend, infrastructure, and data.