← Back to Careers

AI Engineer

Apply Now

Remote

Posted on: January 5, 2026

What Is the role?

We are looking for an AI Engineer who can build and ship AI-powered applications — not just prototype them. You’ll design RAG pipelines, build AI agents, integrate foundation models into real products, and keep them running reliably in production on AWS and Azure. This is a hands-on engineering role, not a research role.

Key Responsibilities

AI Application Development:

  • Build production RAG systems: chunking strategies, embedding pipelines, retrieval, reranking, and response generation
  • Design and implement AI agents using LangGraph or similar frameworks for multi-step reasoning and tool use
  • Integrate foundation models (Claude, GPT, Llama, Mistral) via AWS Bedrock and Azure AI Foundry into existing applications
  • Implement structured output, function calling, and tool use patterns for reliable model interactions
  • Build and maintain prompt templates, manage prompt versioning, and iterate based on evaluation results

AI Infrastructure & Operations:

  • Deploy and manage AI workloads on AWS Bedrock and Azure AI Foundry
  • Set up observability for AI systems — tracing, latency monitoring, token usage, and quality metrics using tools like LangSmith or Langfuse
  • Implement evaluation pipelines: automated evals, LLM-as-judge, and regression testing for model outputs
  • Manage vector databases for semantic search (Pinecone, Qdrant, or pgvector)
  • Optimize costs: model selection, caching, batching, and routing between models based on task complexity

Safety & Quality:

  • Implement guardrails for content filtering, PII detection, and hallucination mitigation
  • Design fallback strategies for when models fail or produce low-confidence outputs
  • Build human-in-the-loop review workflows where needed

General:

  • Write clean, testable Python (and/or TypeScript) code
  • Containerize AI services with Docker and deploy to cloud infrastructure
  • Collaborate with product and engineering teams to identify where AI adds real value

Required Skills

AI/ML Fundamentals:

  • 2+ years building AI-driven applications that run in production (not just notebooks)
  • Strong understanding of how LLMs work: tokenization, context windows, temperature, and their practical implications
  • Hands-on experience building RAG systems: document ingestion, chunking, embeddings, retrieval strategies, and reranking
  • Prompt engineering that goes beyond basics: structured outputs, chain-of-thought, few-shot examples, and system prompts
  • Experience with at least one agent framework (LangGraph, LangChain, or LlamaIndex) for building multi-step workflows

Cloud AI Platforms:

  • Production experience with AWS Bedrock or Azure AI Foundry (model access, guardrails, knowledge bases)
  • Familiarity with managed AI services: AWS Bedrock Agents, Azure AI Search, Azure Document Intelligence
  • Understanding of model selection trade-offs: cost, latency, quality, and context window size

Observability & Evaluation:

  • Experience setting up tracing and monitoring for AI systems (LangSmith, Langfuse, or similar)
  • Ability to design and run evaluation pipelines: automated scoring, LLM-as-judge, and regression tests
  • Understanding of key metrics: latency, token usage, retrieval relevance, answer quality

Vector Databases & Search:

  • Hands-on experience with at least one vector database (Pinecone, Qdrant, pgvector, or Weaviate)
  • Understanding of embedding models, similarity search, and hybrid search (vector + keyword)

Engineering:

  • Strong Python skills — this is your primary language
  • Experience with Docker and containerized deployments
  • Comfortable with Git, CI/CD, and working in a team codebase
  • Basic cloud infrastructure knowledge (AWS or Azure)

Preferred Skills

Advanced AI:

  • Experience with fine-tuning (LoRA, QLoRA) for domain-specific use cases
  • Knowledge of MCP (Model Context Protocol) for connecting AI agents to external tools and data
  • Multi-agent system design and orchestration patterns
  • Streaming architectures for real-time AI responses
  • Synthetic data generation for training and evaluation

Cloud & Infrastructure:

  • AWS SageMaker for custom model hosting
  • Azure AI Studio for model experimentation and deployment
  • Infrastructure as Code (CDK, Terraform) for AI infrastructure
  • Kubernetes for scaling AI workloads

Additional:

  • Experience with multimodal AI (vision + text)
  • Knowledge of AI security: prompt injection prevention, data leakage mitigation
  • Cost optimization strategies for LLM-heavy workloads (caching, model routing, batching)
  • TypeScript/Node.js for building AI-powered APIs alongside Python services

Personal Qualities

  • You debug systematically — AI systems fail in non-obvious ways and you’re patient enough to trace through them
  • Clear communicator — can explain model behavior and trade-offs to non-AI teammates
  • Pragmatic about tool choices — you pick what works, not what’s trending
  • Comfortable with ambiguity — AI projects often require experimentation before a clear path emerges
  • Keeps up with the field without chasing every new paper or framework

We offer you

  • Competitive Compensation
  • Professional Growth
  • Cutting-Edge Technologies
  • Highly motivated & collaborative Team
  • Challenging Projects
  • Work-Life Balance
  • Opportunities for Advancement
  • Employee Well-being
Apply Now