AI Engineer

Whitehall Resources; Województwo mazowieckie; On-site; PLN 350,000 - 650,000; Full time

Job summary

Whitehall Resources Limited is seeking an experienced AI Engineer to design and deliver production-grade AI-native software. You will own end-to-end LLM-enabled solutions, collaborate with customer teams, and drive architecture decisions for scalable deployments.

The role requires strong backend and frontend skills (Python/Node.js/Java, React/Angular) and deep experience with LangChain, Semantic Kernel, and vector search.

Qualifications

• 10+ years of software engineering experience, incl. customer-facing or embedded contexts.
• Backend (Python, Node.js, Java) and frontend (React, Angular) proficiency.
• Experience designing AI-native software for production environments.
• Familiarity with LangChain, Semantic Kernel, prompt chaining, vector search, and context management.

Responsibilities

• Own end-to-end delivery of LLM-enabled applications in agile sprints (backend, data orchestration, LLM pipelines, UI).
• Embed with customers in the field, including onsite work up to 30% travel.
• Build APIs (REST/GraphQL), orchestration pipelines, vector DB integrations, LLM frameworks, and UI components (React/Angular).
• Contribute to shared SDKs, tools, and platform roadmap.
• Ensure performance, reliability, and security with monitoring and observability.
• Deploy and operate in the cloud (AWS/Azure/GCP) with CI/CD, containers, and infra-as-code.
• Provide engineering leadership from zero to one and balance user value with scalability.

Skills

Python

Node.js

Java

React

Angular

LLM tooling

LangChain

Semantic Kernel

Vector search

CI/CD

Tools

REST/GraphQL

AWS

Azure

GCP

Containers

IaC

Job description

Whitehall Resources currently require an experienced AI Engineer to work with a key client

Experience Required:

• Experience: In leveraging or critically thinking about how to integrate AI into work processes, decision-making, or problem-solving. This may include using AI-powered tools, automating workflows, analyzing AI-driven insights, or exploring AI’s potential impact on the function or industry
• Relevant Experience: 8+ years of software engineering, including 2+ years building systems in customer-facing or embedded roles
• System architecture: Proven ability to design and implement AI-native software in production environments
• Engineering depth: Strength in backend (Python, Node.js, Java), frontend (React, Angular), APIs (REST/GraphQL)
• LLM tooling: Familiarity with LangChain, Semantic Kernel, prompt chaining, vector search, and context management
• Performance & observability: Skilled in debugging distributed systems, tuning for latency, and implementing monitoring
• Platform mindset: Can contribute to shared SDKs and tools, raising engineering velocity for the whole org
• Product sensibility: Prioritize for user value, MVP iteration, and long-term scale
• DevOps fluency: Experience deploying in AWS, Azure, or GCP with CI/CD, containers, and infra-as-code

Responsibilities:

1. 1. Build and deliver production-ready AI solutions
   Own end-to-end delivery of LLM-enabled applications in agile sprints, spanning backend services, data orchestration, LLM pipelines, and front-end UI
   Act as the “CTO of the build,” making architecture and implementation decisions
   Ensure solutions convert into scaled production deployments
2. 2. Embed with customers in the field
   Work side-by-side with strategic customer teams, often onsite (up to 30% travel)
   Diagnose root problems, understand context and customer pain points, and identify high-value AI opportunities
   Adapt, deploy, and iterate in live environments
3. 3. Engineer across the full stack
   Build APIs (REST/GraphQL), orchestration pipelines, vector DB integrations, LLM frameworks (LangChain, Semantic Kernel), and UI components (React/Angular)
   Integrate with legacy systems and navigate ambiguity while shipping safely at speed
   Create libraries, SDKs, prompts, scaffolds, and documentation that can be reused across customer engagements
   Turn each successful project into a repeatable pattern
4. 5. Influence the platform and product
   Share field-tested insights with platform and product teams
   Shape internal tooling and contribute to the Now AI Platform roadmap and primitives
5. 6. Ensure performance, reliability, and security
   Debug distributed systems, tune for latency, and implement monitoring and observability
   Deliver resilient, secure systems suitable for high-stakes enterprise contexts
6. 7. Deploy and operate in the cloud
   Use AWS, Azure, or GCP with CI/CD, containers, and infrastructure-as-code
7. 8. Provide engineering leadership
   Lead implementation from zero to one, earning trust from architects, PMs, and customer teams
   Balance product sensibility (user value, MVP iteration) with long-term scalability

Summary in One Line

The candidate is expected to be a hands-on, customer-facing, full-stack AI engineer who rapidly builds and deploys production-grade GenAI solutions for strategic customers, then packages those learnings into reusable assets that strengthen the platform.

Key Requirements at a Glance

• 10+ years of software engineering experience (2+ in customer-facing or embedded roles)
• Backend (Python, Node.js, Java) and frontend (React, Angular) strength