Senior AI Engineer | On-site - Islamabad (Hybrid) | PKR Salary

About the Company:

Hiring for an AI-native commercial insurance brokerage.

Role Overview – Senior AI Engineer

You have shipped production AI systems end to end, distributed services, trained models, and retrieval pipelines. You own architecture decisions, you measure what you ship, and you reason about cost, failure, and quality before writing code. This is a broad, high-ownership role spanning automation infrastructure, applied ML, and knowledge/ RAG systems. We are not looking for someone who has done all of it perfectly; we are looking for someone who has done enough of it in production to learn the rest fast.

Core Responsibilities

Distributed automation:

• Re-architect a single-machine automation engine into a system handling 1,000+ concurrent jobs against third-party portals: microservices, persistent browser session pools, container orchestration.

• Design the job queue and execution model: dispatch, retry, per-target rate limiting, circuit breakers, real-time status feed to the user-facing UI.

• Build an onboarding engine that, given a portal URL and credentials, discovers fields, maps them to our internal schema, and generates a working automation script with no manual scripting.

ML & model quality:

• Replace heuristic scoring with supervised models trained on historical outcome data; design and train domain-specific risk and recommendation models.

• Benchmark against LLM-only baselines and pick the right tool per problem.

• Stand-up eval harnesses on every model, runnable on demand and on a schedule, that catch regressions before production.

• Own the R&D track for self-hosted inference (LLMs, embeddings, ASR, TTS) and deliver cost-vs-quality memos that drive build/buy decisions.

Knowledge pipelines & RAG:

• Build automated change-detection pipelines that monitor third-party documents and portal UIs and trigger extraction on updates.

• Parse unstructured documents into a hierarchical schema with confidence levels and source provenance.

• Own RAG quality — chunking, embedding selection, retrieval tuning, query-time context assembly — so every AI answer cites the right clause from the right document version.

• Resolve conflicts when two sources disagree on the same rule.

Hard Requirements

• Python (FastAPI, async/await): production service design, not scripts.

• Distributed job execution with Celery + Redis or equivalent, Postgres as job store; you have debugged retry storms and backpressure in production.

• Kubernetes or Docker Swarm: deployed and operated, not tutorial-level.

• Browser automation at scale: Playwright or Puppeteer handling MFA flows, session persistence, and anti-bot systems (isTrusted events, PerimeterX-class protection).

• Python ML stack: PyTorch or equivalent, scikit-learn, HuggingFace; you build training pipelines, not just call APIs.

• Supervised learning and embeddings: labels, class imbalance, and clean feature pipelines from messy source data.

• RAG shipped beyond demo quality: chunking, retrieval tuning, structured-output prompting, output validation, and hallucination detection on real, inconsistent documents.

• Vector databases: pgvector (our stack) or equivalent, with a clear grasp of chunking tradeoffs.

• Eval-first mindset: every model and knowledge system ships with a benchmark for correctness, freshness, and attribution.

• You wrangle, label, and pipeline your own data, and treat provenance, confidence scoring, and freshness tracking as defaults, not options.

• You reason about cost-per-job, failure blast radius, and queue depth before writing code

Strong Plus

• LLM integration for DOM and field inference (vision models).

• LLM fine-tuning/ RLHF.

• SageMaker or equivalent for model serving; inference cost benchmarking across providers (Anthropic, OpenAI, self-hosted).

• Regulated-domain experience (insurance, fintech, health, legal) — knowing what you are reading matters.

• Web scraping and change-detection infrastructure (PDF diffing, DOM monitoring).

• DigitalOcean infrastructure experience

Other Details:
Experience: 4-5 years
Location: Islamabad (Hybrid)
Office Days: Monday to Saturday

About HR Ways HR Ways is an award-winning Technical Recruitment Firm helping software houses and IT Product companies internationally and locally to find IT Talent. HR Ways is engaged by 300+ Employers worldwide, ranging from the world's biggest SaaS Companies to the most competitive Startups. We have entities in Dubai, Canada, the US, the UK, Pakistan, India, Saudi Arabia, Portugal, Brazil, and other parts of the world. Join our WhatsApp Channel https://whatsapp.com/channel/0029VamSiLr5fM5fMtAdCS2M to stay updated, or visit www.hrways.co to know more.