Senior Agentic AI Engineer

Key ResponsibilitiesArchitect & Build Agents: Design, develop, and refine sophisticated, multi-step AI agents that can reason, plan, and execute complex software engineering tasks. Integrate SWE Tools: Seamlessly integrate agents within the C++ ecosystem (build systems, debuggers, profilers, and static analyzers) for programmatic code comprehension and modification. Develop Agentic Frameworks: Innovate on agentic methodologies (ReAct, CoT, LangGraph) and manage multi-agent systems. Build Data Pipelines: Create telemetry frameworks to capture agent trajectories (state, action, observation) for generating high-quality datasets for fine-tuning. Manage RAG Systems: Optimize RAG pipelines utilizing vector databases and code-specific embedding models (e.g., GraphCodeBert) for efficient knowledge retrieval. Design Sandboxed Environments: Develop remote execution environments (using Docker, Firecracker) to safely build and run C++ code. Collaborate on Infrastructure: Partner with the backend team to create APIs (gRPC, REST) and cloud infrastructure (Kubernetes, GCP/AWS) to support agentic systems. Qualifications & SkillsStrong theoretical and practical understanding of LLMs: In-depth knowledge of transformer architectures, attention mechanisms, fine-tuning techniques (LoRA, QLoRA), and retrieval-augmented generation (RAG). Significant experience in building LLM agents: Proven ability to design, implement, and evaluate complex, multi-step agents that can reason, plan, and utilize tools. Exceptional programming skills in C++ and familiarity with the developer ecosystem.