M
Posted 5 hours ago
Member of Technical Staff - Code Generation
MoonlakeMember of Technical Staff - Code Generation
Requirements
Experience shipping agentic systems, Expertise in post-training (SFT, DPO, RLHF), Knowledge of agent frameworks, Experience with sandboxed execution and security
Skills
LLMPythonRLHF
About the role
About the Company
Moonlake is building AI for creating real-time interactive content.
Responsibilities
- Design agentic systems including tool catalogs, function calling, and program synthesis/repair loops
- Implement control patterns such as ReAct, Reflexion, ToT, and LangGraph-style architectures
- Build evaluation task suites for multi-step coding tasks
- Develop full-stack LLM engineering components including prompt libraries, routing, and KV-cache management
- Manage security and isolation using Docker, firejail, and network egress controls
- Execute post-training workflows including supervised fine-tuning and preference/trace RL (DPO/RLAIF/RLHF)
- Curate datasets and perform reward shaping and safety filtering
Requirements
- Experience shipping agents that pass end-to-end test suites for real repositories
- Proven track record in agentic systems or code generation
- Experience building datasets from execution traces
- Proficiency in agent frameworks or OSS evaluations (e.g., LangGraph, AutoGen, SWE-bench)
- Expertise in post-training techniques like DPO, RLAIF, or RLHF
ScoutJobs Agent
Get matches like this delivered daily
Sign up free — we'll pull jobs that fit your CV from across the web and rank them for you.
Get started — it's freeMember of Technical Staff - Code Generation
Moonlake · San Mateo
