LLM Platform Engineer/Lead (m/f/d)

Hello 👋 I am Servesh, Co- founder and CTO at Kayzen, and I am now looking for a LLM Platform Engineer/Lead who will be part of our Engineering team. 🙌 But wait, you have not heard of Kayzen before? 😃

Kayzen is a mobile demand-side platform (DSP) dedicated to democratizing programmatic advertising. We enable leading apps, agencies, media buyers, and brands to run programmatic customer acquisition, retargeting, and brand performance campaigns through its self-serve and managed service options. Built on the three core pillars of performance, transparency, and control, Kayzen powers the world’s best mobile marketing teams with bespoke solutions that fuel business growth and deliver a competitive advantage. With an unprecedented scale of 160B+ daily ad requests from 1.6B+ unique users worldwide, we serve up to 1B+ ads per day in 180 countries. Kayzen is accessible through our APIs and user interface.

The Platform Engineering team owns Real-time bidding (RTB) platform, a Real-time budget system, Real-time event processing, Stream data processing engine and multiple other complex large-scale distributed components and data pipelines. We work closely with data scientists, data analysts, product and business teams. We are responsible for some of the most technically challenging work, for example:

• Handling ~2 Million Req/sec in sub-millisecond latency
• Handing & managing ~Petabytes of data
• Managing distributed systems deployed across multiple data centers
• Optimizing JVM and Linux kernel for optimal performance
• Managing our own data center spread across the globe consisting of thousand of powerful servers
• Working on some of the most challenging problems of Ad-Tech

Sounds interesting. Isn't it?

We are looking for an  LLM Platform Engineer  /Lead who can  evangelise AI across the company  and build the  foundational tooling, frameworks, and workflows  that allow teams to ship AI-powered features quickly and safely. This role is ideal for an engineer who understands modern AI capabilities and focuses on  developer velocity, reuse, and production readiness  rather than training complex models from scratch.

• →Design and build  internal AI frameworks, SDKs, and shared libraries 
• →Enable teams to integrate AI features with minimal friction
• →Set up  standardized patterns  for using LLMs, embeddings, agents, and workflows
• →Build reusable components for  prompt management, evaluation, observability, and safety 
• →Define best practices for  AI usage, cost control, and reliability 
• →Evangelise AI internally through documentation, examples, and hands-on guidance
• →Rapidly prototype AI-powered features and turn them into reusable building blocks
• →Own AI tooling from experimentation to production

• Hands-on experience with  LLM APIs  (OpenAI, Anthropic, etc.)
• Experience with  RAG pipelines, embeddings, vector databases 
• Familiarity with  prompt engineering, prompt versioning, and evaluation 
• Experience with  AI orchestration frameworks 
• Understanding of  AI observability, cost monitoring, and failure modes
• You’ve shipped at least one LLM-powered feature to production and iterated based on telemetry or user feedback.
• Comfortable with embeddings, fine-tuning, vector search, tokenization, and evaluation methodologies.
• Familiar with data lakes/warehouses, feature stores, and streaming/batch ETL; cloud (AWS/GCP/Azure).

• Excellent  Python  skills (required)
• Experience building  frameworks, platforms, or developer tooling 
• Strong understanding of  APIs, services, and system design 
• Writes clean, maintainable, production-grade code

• Bias for shipping and iteration
• Can translate AI complexity into simple abstractions
• Comfortable with ambiguity and rapid change
• Thinks in terms of  leverage and reuse , not one-off solutions

• Heavy model training or research
• Designing custom ML algorithms
• Academic optimization work.

• Experience with  agent-based systems  and tool calling
• Experience setting up  guardrails, moderation, and safety checks 
• Familiarity with  Docker, cloud infra, and CI/CD 
• Prior work in  platform teams or enablement roles