Senior Agentic AI Engineer

About UsAt SkyLabs AI Inc., we are at the forefront of the artificial intelligence revolution. As a US-headquartered company, we conduct applied research on AI for intelligent reasoning. We specialize in complex neurosymbolic AI to solve intricate problems within software engineering. Our team is composed of world-class researchers and engineers dedicated to building the platforms and intelligent agents that will power the next generation of software. If you are passionate about building truly intelligent systems and want to make a lasting impact, join us.The RoleWe are seeking an exceptional Senior Agentic AI Engineer to join our core team. This is not a typical AI role; you will be responsible for architecting, building, and deploying complex, autonomous AI agents designed to reason about and operate within the C++ software engineering lifecycle.You will be building agents that can programmatically interact with compilers (LLVM), debuggers (GDB/LLDB), build systems (CMake/Bazel), and static analysis tools to understand, modify, and build complex C++ codebases. The ideal candidate is a master programmer with a deep, practical understanding of both agentic AI and the C++ developer ecosystem.RequirementsKey ResponsibilitiesArchitect & Build Agents: Design, develop, and refine sophisticated, multi-step AI agents that can reason, plan, and execute complex software engineering tasksIntegrate SWE Tools: Natively integrate agents with the C++ ecosystem (build systems, debuggers, profilers, and static analyzers) to enable programmatic code comprehension and modificationDevelop Agentic Frameworks: Implement and innovate on agentic patterns (ReAct, CoT, LangGraph) and orchestrate multi-agent systemsBuild Data Pipelines: Design telemetry systems to capture agent trajectories (state, action, observation) to create high-quality datasets for fine-tuningManage RAG Systems: Implement and optimize RAG pipelines using vector databases and code-specific embedding models (e.g., GraphCodeBert) for knowledge retrievalDesign Sandboxed Environments: Develop remote execution environments (using Docker, Firecracker) where agents can safely build and run C++ codeCollaborate on Infrastructure: Work with the backend team to design APIs (gRPC, REST) and cloud infrastructure (Kubernetes, GCP/AWS) to support the agentic systemsQualifications & SkillsCore Profile: Agentic AI DeveloperExcellent theoretical and practical knowledge of LLMs: Deep understanding of transformer architectures, attention mechanisms, fine-tuning techniques (LoRA, QLoRA), and retrieval-augmented generation (RAG)Vast experience in building LLM agents: Proven track record of designing, implementing, and evaluating complex, multi-step agents that can reason, plan, and use toolsExcellent development skills in Python: Mastery of Python for AI/ML development, data processing, and backend service integrationStrong Computer Science (CS) background: Solid foundation in algorithms, data structures, operating systems, and software engineering principlesSpecific Experience Required:Who You Are Agentic Frameworks & LLM OperationsAdvanced Prompt Engineering: Demonstrable experience with reasoning-and-action (ReAct), Chain of Thought (CoT), and graph-based agent structures (e.g., LangGraph) to handle complex, long-horizon tasksAgent Orchestration Frameworks: Hands-on experience with frameworks like LangGraph for coordinating multiple agents and managing complex stateRAG: Vector databases, embedding models for code (e.g., GraphCodeBert) and Graph Vector DBs based on ASTsLLM Evaluation & Benchmarking: Experience with code generation benchmarks, specifically SWE-bench (and knowledge of its variants like SWE-bench++), to rigorously test and improve model performanceTelemetry & Fine-Tuning Pipelines: Designing data collection systems (telemetry) to capture agent trajectories (state, action, observation) for creating high-quality datasets for model fine-tuning C++ & Software Engineering (SWE) ToolingDeep C++ Ecosystem Knowledge: This is non-negotiable. Must have experience with the tools the agent will use, including:Build Systems: CMake, Make, and preferably BazelDebuggers: GDB, LLDB, and their programmatic interfacesProfilers: perf, Valgrind, or other C++ performance analysis toolsIDE Extension / Language Server Protocol (LSP): Experience building IDE plugins (for VS Code, CLion, etc.) or familiarity with the Language Server Protocol (LSP) to understand how an agent can programmatically interact with an IDE's core features (e.g., "find all references," "go to definition") Program AnalysisStatic & Dynamic Analysis: Understanding of static analysis (e.g., Clang-Tidy, Clang Static Analyzer) and how to parse their output to guide an agent's code modificationsAbstract Syntax Trees (ASTs): Experience using tools like Clang's LibTooling or Tree-sitter to programmatically parse, analyze, and perform "surgical changes" to C++ code, which is far more reliable than text-based regex Backend & Cloud InfrastructureRemote Execution & Sandboxing: Experience with container technologies (Docker, Firecracker) and remote execution environments to create the "remote sandbox" where agents can safely build and run codeAPI & Protocol Design: Experience designing and integrating with RPC/API protocols (gRPC, REST) to handle communication between the IDE plugin, the backend, and various agent serversCloud Services & Databases: Proficiency with a major cloud provider (AWS, GCP, Azure), database management (SQL/NoSQL), and cloud-native orchestration tools (e.g., Kubernetes) for managing the agent orchestration and backend infrastructureYou are a builder at heart, driven by curiosity and a desire to solve hard problems. You don't wait for instructions; you identify opportunities and seize them. You are comfortable with ambiguity and thrive in a fast-paced, innovative environment where you are encouraged to experiment and push boundaries. You are a clear communicator who can articulate complex technical concepts and work collaboratively to achieve ambitious goals.BenefitsWhat We OfferCompetitive salary in USDComprehensive health allowanceRelocation allowance (if you're moving to Islamabad)Monthly team events and offsitesA beautiful, collaborative office spaceWork alongside world-class AI researchers and engineers