AI Platform Engineer

We are looking for an AI Engineer to help shape and build the next generation of AI-powered engineering and operational capabilities across the organization. This role focuses on integrating modern AI technologies into internal workflows, engineering processes, operational visibility, knowledge management, and product capabilities.
The ideal candidate is hands-on, highly technical, and passionate about building practical AI systems — especially around LLMs, RAG architectures, vector databases, observability integrations, and AI-assisted automation.
This position will play a foundational role in transforming the company into an AI-oriented engineering organization.
 
Responsibilities

1. AI Platform & Infrastructure

• Design and implement internal AI infrastructure and services
• Build and maintain Retrieval-Augmented Generation (RAG) systems
• Design vector database architecture for organizational knowledge and context persistence
• Integrate AI systems with internal services, APIs, documentation, logs, and operational tools
• Create scalable pipelines for ingestion, embedding, indexing, and retrieval of company knowledge

2. Knowledge & Context Engineering

• Build systems that transform company knowledge into searchable AI context
• Integrate technical documentation, runbooks, incidents, tickets, APIs, Swagger/OpenAPI specs, architecture docs, and operational procedures into vectorized knowledge layers
• Design metadata, chunking, embedding, and retrieval strategies
• Improve relevance, context quality, and response accuracy of AI systems

3. AI-Powered Engineering Initiatives

• Develop AI assistants and copilots for engineering teams
• Build AI workflows for:Incident analysis & RCA

. Operational monitoring
. Deployment intelligence
. Technical support
. Internal documentation
. Developer productivity

• Explore AI-assisted software engineering workflows and automation opportunities

4. Observability & Operations Integration

• Integrate AI with monitoring and observability platforms such as:Prometheus

. VictoriaMetrics
. Elasticsearch
. OpenTelemetry
. Grafana
. Logging and tracing systems

• Build intelligent operational insights and anomaly detection systems
• Help establish AI-driven NOC and incident management capabilities

5. Research & Innovation

• Continuously evaluate emerging AI technologies and frameworks
• Prototype and validate new AI-driven approaches
• Contribute to long-term AI architecture and strategy
• Help define AI governance, security, and operational standards

 
Technical Requirements
Strong Experience With

• Python development
• APIs and backend engineering
• LLMs and AI application development
• Vector databases such as:Qdrant

. Pinecone
. Weaviate
. Milvus

• RAG architectures and semantic search
• Embedding models and retrieval pipelines
• Docker and Kubernetes
• Git and CI/CD workflows

Familiarity With

• LangChain / LlamaIndex / DSPy
• OpenAI APIs or equivalent AI providers
• Prompt engineering
• AI agents and tool calling
• Elasticsearch and observability stacks
• Kafka or event-driven systems
• Distributed systems architecture
• Cloud platforms (Azure, AWS, GCP)

 
Preferred Qualifications

• Experience building production AI systems
• Experience integrating AI with enterprise systems
• Understanding of observability and operational tooling
• Strong system design and architecture skills
• Familiarity with software engineering workflows and developer tooling
• Ability to work independently and prototype quickly

 
What Success Looks Like

• Internal AI assistants become part of daily engineering workflows
• Company knowledge becomes AI-searchable and context-aware
• Faster incident investigation and operational visibility
• Improved developer productivity through AI tooling
• Establishment of a scalable AI platform foundation for future initiatives

 
Mindset We’re Looking For

• Builder mentality
• Strong curiosity and experimentation mindset
• Pragmatic problem solving
• Passion for emerging technologies
• Ownership and autonomy
• Ability to bridge infrastructure, engineering, and AI domains

 
Nice-to-Have Experience

• MCP (Model Context Protocol)
• AI memory/context systems
• Fine-tuning or model evaluation
• Knowledge graph systems
• AI security and governance
• Multi-agent orchestration systems
• AI-assisted DevOps/SRE workflows

Benefits

• Transportation discount and voucher
• Organizational food discount
• Learning budget
• Team Building Budget
• Wellness Budget
• Comprehensive health, dental, and vision insurance