Gen AI ENGINEER

Tkxel; Pakistan; On-site; PKR 1,500,000 - 2,300,000; Full time

Job summary

Tkxel seeks a full-stack GenAI engineer to design, build, and iterate on real-time AI solutions in collaboration with client teams. You will operate at the nexus of backend engineering and applied AI, delivering end-to-end architectures and deploying them in production environments.

Responsibilities include developing multi-agent GenAI systems, RAG pipelines, and agentic frameworks, with direct client exposure to translate business problems into deployable AI use cases and fast iteration cycles.

Qualifications

• Strong GenAI expertise with LLMs, prompt engineering, RAG, agentic frameworks.

Responsibilities

• Design and build production-grade GenAI systems: multi-agent architectures, RAG pipelines over enterprise-scale document stores, and real-time systems.
• Build agentic systems that reason, retrieve, and act — not just conversational responders.
• Work directly with client stakeholders to translate ambiguous business problems into scoped, deployable AI use cases.
• Rapidly prototype and iterate on-site/embedded with the client, compressing feedback loop between idea and working solution.
• Own solutions end-to-end — architecture, implementation, evaluation, and handoff.
• Bridge technical and business conversations: explain trade-offs to non-technical stakeholders and translate priorities back into technical decisions.

Skills

GenAI expertise

Python

FastAPI/Django

Azure/AWS

Job description

Job Description:

We're looking for a full-stack GenAI engineer who can operate directly with client to design, build, and iterate on AI solutions in real time against live business problems, not just ship code from behind a backlog. This role sits at the intersection of backend engineering and applied AI.

Key Responsibilities

• Design and build production-grade GenAI systems: multi-agent architectures, RAG pipelines over large/enterprise-scale document stores, and real-time systems used in daily business operations
  

• Build agentic systems that reason, retrieve, and act — not just conversational responders
  

• Work directly with client stakeholders to translate ambiguous business problems into scoped, deployable AI use cases
  

• Rapidly prototype and iterate on-site/embedded with the client, compressing the feedback loop between idea and working solution
  

• Own solutions end-to-end — architecture, implementation, evaluation, and handoff — rather than working purely from fixed specs
  

• Bridge technical and business conversations: explain trade-offs to non-technical stakeholders and translate priorities back into technical decisions
  

Requirements

• Strong GenAI expertise — hands-on experience with LLMs, prompt engineering, RAG, agentic frameworks, and multi-agent design; comfortable working across multiple model providers
  

• Core stack: Python, FastAPI/Django, and Azure or AWS
  

• Applied depth in the hard parts, e.g.:

  • Permission-aware retrieval at scale
    

  • Async task orchestration
    

  • LLM evaluation and observability
    

• Business understanding — able to grasp a clients operating model and pressure-test whether a proposed AI use case creates measurable value, not just technical novelty
  

• Forward-deployed mindset — thrives working embedded with clients rather than at arms length; comfortable with ambiguity, direct client exposure, and fast iteration cycles typical of an FDE role
  

• Strong communication skills — able to run discovery sessions, present to leadership, and document decisions clearly.
  

Requirements: