Senior Applied AI Engineer (LLM & Multi-Agent Systems)

We are looking for a highly technical Senior Applied AI Engineer to design, build, and scale production-grade AI systems powered by LLMs, multi-agent architectures, and retrieval-based intelligence.

This role is ideal for engineers who have already deployed AI products into real-world environments and understand the operational challenges of production AI systems beyond prototypes or demos.

You will work closely with product and engineering teams to architect reliable, scalable, and observable AI infrastructure capable of serving real users at scale.

What You’ll Build

• Production-ready LLM applications and AI workflows
• Multi-agent orchestration systems with robust state management
• Retrieval-Augmented Generation (RAG) pipelines using vector databases
• AI inference orchestration and model routing systems
• Structured output pipelines with validation and retry logic
• Feedback loops and learning systems for continuous improvement
• Scalable multi-tenant AI architectures

Key Responsibilities

• Design and implement scalable AI/LLM architectures for production environments
• Build reliable multi-agent systems with error isolation and orchestration control
• Develop high-performance inference pipelines and AI workflows
• Optimize prompt engineering, structured outputs, and function calling
• Implement embedding pipelines and retrieval systems using vector databases
• Create monitoring, evaluation, and observability frameworks for AI systemsCollaborate with backend teams on Python and Node.js service integrations
• Improve model quality through fine-tuning and evaluation strategies
• Ensure scalability, reliability, and cost efficiency across AI services

Required Experience

• 3+ years of experience building applied AI/ML systems
• Proven experience deploying LLM-based applications into production
• Strong Python engineering skills in production environments
• Experience with async workflows, testing, packaging, and observability
• Hands-on experience with Anthropic SDK and/or OpenAI APIs
• Experience building RAG systems using vector databases
• Strong understanding of AI/agent failure modes:
  • hallucinations
  • loop control
  • state corruption
  • cost runaway
• Experience designing multi-agent workflows and orchestration systems
• Strong system design and architecture fundamentals
• Experience designing scalable inference and evaluation pipelines

Core Stack

• Python
• OpenAI SDK
• Anthropic SDK
• pgvector
• LangGraph / CrewAI
• AWS (S3, ECS, SageMaker)

Nice to Have

• Pinecone
• Weaviate
• Node.js / TypeScript
• Fine-tuning on domain-specific datasets
• RLHF / RLAIF
• Multi-tenant ML architectures

What We’re Looking For

We are looking for engineers who think beyond prompts and prototypes.

The ideal candidate has experience building reliable AI systems that operate in production, can reason about architecture and scalability, and understands the trade-offs between model quality, latency, reliability, and operational cost.

Important Note

This role is NOT focused on experimentation-only or prompt-only engineering.

We are specifically looking for engineers who have deployed AI systems into production environments.

Why Join Us?

• Opportunity to work on cutting-edge AI systems
• High technical ownership and architectural impact
• Real production-scale AI challenges
• Collaborative engineering environment
• Fast-moving and innovation-driven team