Skip to content
CV Rocket
Get started
How it worksThe enginePricingBlogContactSign in

Open nowPosted 276 days ago

Senior Agentic AI Engineer

Workable (global search)108,016 open roles

Where
Islamabad, Islamabad Capital Territory, Pakistan
Get the CV for this job

From $25 per CV, paid once. No subscription.

Your applicationOpen nowSenior Agentic AI EngineerWorkable (global search) · Islamabad, Islamabad Capital Territory, Pakistan

  1. YouYes, apply to this one.

  2. CV RocketCV written for this posting.

  3. 25 readersRecruiter, hiring manager, skeptic. Round after round.

  4. CV RocketApplied on Workable (global search)'s own form.

The reply lands in your private mailbox

3×more interviews than doing it yourself with ChatGPT.

The clock on this job

Early applications get read.

7.9% of postings close within 7 days. Measured by our own scanner across the market. Workable (global search) postings stay open a median of 7 days.

Share of postings closed within
  1. 1.6%1 day
  2. 3.6%3 days
  3. 7.9%7 days
  4. 14.9%14 days
  5. 34.0%30 days
This job: posted 276 days ago

Workable (global search) median: 7 days open

The posting

About Us

At 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 Role

We 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.

Requirements

Key Responsibilities

  • Architect & Build Agents: Design, develop, and refine sophisticated, multi-step AI agents that can reason, plan, and execute complex software engineering tasks.
  • Integrate SWE Tools: Natively integrate agents with the C++ ecosystem (build systems, debuggers, profilers, and static analyzers) to enable programmatic code comprehension and modification.
  • Develop Agentic Frameworks: Implement and innovate on agentic patterns (ReAct, CoT, LangGraph) and orchestrate multi-agent systems.
  • Build Data Pipelines: Design telemetry systems to capture agent trajectories (state, action, observation) to create high-quality datasets for fine-tuning.
  • Manage RAG Systems: Implement and optimize RAG pipelines using vector databases and code-specific embedding models (e.g., GraphCodeBert) for knowledge retrieval.
  • Design Sandboxed Environments: Develop remote execution environments (using Docker, Firecracker) where agents can safely build and run C++ code.
  • Collaborate on Infrastructure: Work with the backend team to design APIs (gRPC, REST) and cloud infrastructure (Kubernetes, GCP/AWS) to support the agentic systems.

Qualifications & Skills

Core Profile: Agentic AI Developer

  • Excellent 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 tools.
  • Excellent development skills in Python: Mastery of Python for AI/ML development, data processing, and backend service integration.
  • Strong Computer Science (CS) background: Solid foundation in algorithms, data structures, operating systems, and software engineering principles.

Specific Experience Required:

1. Agentic Frameworks & LLM Operations

  • Advanced 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 tasks.
  • Agent Orchestration Frameworks: Hands-on experience with frameworks like LangGraph for coordinating multiple agents and managing complex state.
  • RAG: Vector databases, embedding models for code (e.g., GraphCodeBert) and Graph Vector DBs based on ASTs.
  • LLM Evaluation & Benchmarking: Experience with code generation benchmarks, specifically SWE-bench (and knowledge of its variants like SWE-bench++), to rigorously test and improve model performance.
  • Telemetry & Fine-Tuning Pipelines: Designing data collection systems (telemetry) to capture agent trajectories (state, action, observation) for creating high-quality datasets for model fine-tuning.

2. C++ & Software Engineering (SWE) Tooling

  • Deep C++ Ecosystem Knowledge: This is non-negotiable. Must have experience with the tools the agent will use, including:
  • Build Systems: CMake, Make, and preferably Bazel.
  • Debuggers: GDB, LLDB, and their programmatic interfaces.
  • Profilers: perf, Valgrind, or other C++ performance analysis tools.
  • IDE 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").

3. Program Analysis

  • Static & 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 modifications.
  • Abstract 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.

4. Backend & Cloud Infrastructure

  • Remote Execution & Sandboxing: Experience with container technologies (Docker, Firecracker) and remote execution environments to create the "remote sandbox" where agents can safely build and run code.
  • API & Protocol Design: Experience designing and integrating with RPC/API protocols (gRPC, REST) to handle communication between the IDE plugin, the backend, and various agent servers.
  • Cloud 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 infrastructure.

Who You Are

You 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.

Benefits

What We Offer

  • Competitive salary in USD
  • Comprehensive health allowance
  • Relocation allowance (if you're moving to Islamabad)
  • Monthly team events and offsites
  • A beautiful, collaborative office space
  • Work alongside world-class AI researchers and engineers
From $25, paid onceGet the CV for this job

What happens when you press

One press. We do the rest.

  1. A CV for this posting

    Written against Workable (global search)'s own wording, from every piece of relevant proof in your profile.

  2. 25 readers review it

    Recruiter, hiring manager, skeptic and more read every draft, round after round. You get the best round.

    The review screen in CV Rocket: how each CV was read, round by round.

  3. We apply on Workable (global search)'s form

    Our application engine gets through the hardest forms there are. Where a question needs you, AI suggests the best answer. Don't want us applying from our IP addresses? Use our Chrome extension: we apply straight from your own browser.

    An application in CV Rocket: every answer filled in on the employer's form.

  4. Every reply, sorted

    Workable (global search)'s answer lands in your private mailbox, and we classify it on arrival: interview, question, rejection.

    The CV Rocket inbox: each employer reply classified as an interview, an action or a rejection.

  5. Reply with AI

    AI helps you write the email, checks it and sends it. We show you whether the recruiter read it.

  6. The interview in your calendar

    Full integration with your calendar. The invitation goes straight in.

    An interview invitation in the CV Rocket inbox, added to the candidate's calendar.
Get the CV for this job

From $25 per CV, paid once. No subscription.

Why it works

3×

more interviews than doing it yourself with ChatGPT.

ChatGPT writes a CV and never learns what happened to it. We see every reply. For each CV we know:

  • How it was written, and how the review scored it
  • When we applied, and how long after the posting went up
  • Which posting, which company, which city
  • Who got the interview, and who heard nothing

That is how we know which CVs get called.

Get the CV for this job

From $25 per CV, paid once. No subscription.

The numbers game

More applications. More interviews.

Every application goes out with its own CV, written for that posting and paid once. Send enough of them and the law of large numbers finds you the job.

Get the CV for this job
By hand5–10
With CV Rocket100
applications a day

Nearby

Live postings like this one

Same employer first, then the same role elsewhere.

Before you press

Straight answers

Get the CV for this job

From $25 per CV, paid once. No subscription.

What if my background isn't good enough?

We make the most of the background you have. The CV uses every piece of relevant proof your profile holds, and one of the 25 readers reads your whole profile and flags what the CV left out.

Do you really apply for me?

Yes, on the employer's own form, the hardest ones included. Where a question needs you, you answer it right there and AI suggests the best answer. Don't want us applying from our IP addresses? Use our Chrome extension: we apply straight from your own browser.

Is it a subscription?

No. You pay once per CV, from $25. Every application goes out with its own CV, written for that posting.

One job. One CV.
Paid once.

Pick the posting you want. We write for it, apply for you and catch the reply.

Get the CV for this job

From $25 per CV, paid once. No subscription.