Senior Full Stack AI Engineer

Company Description

is dedicated to making AI accessible and practical for small and mid-sized businesses. We focus on creating AI agents that integrate seamlessly with your existing tools and workflows, solving real operational pain points with measurable results. Through collaborative and iterative development, we ensure our AI solutions are intuitive, dependable, and designed to enhance your team's efficiency. By automating repetitive tasks, we empower businesses to deliver faster responses, reduce errors, and improve customer satisfaction. bridges the gap between enterprise-grade AI capabilities and the unique needs of small businesses, helping them grow and deliver greater value to their clients.

About the Role

We are seeking a
Full Stack AI Engineer
to design, build, and deploy production-grade AI applications that integrate deep learning models, vector databases, and cloud-native infrastructure. You'll be responsible for creating scalable, secure, and performant systems that power real-world AI use cases—from intelligent automation to multi-agent orchestration.

This role requires fluency across the full stack: frontend-to-backend development, API integration, container orchestration, and AI model integration. You'll work closely with our AI architects, product team, and DevOps engineers to turn prototypes into production systems.

Key Responsibilities

• Design, build, and deploy AI-driven web applications and APIs using
  LangChain
  ,
  LangGraph
  , and
  OpenAI
  models (GPT series).
• Implement scalable inference pipelines and multi-agent workflows that leverage
  AWS ECS
  ,
  EKS
  , and
  containerized microservices
  .
• Architect secure backend systems with
  AWS Cognito
  ,
  IAM
  , and
  Secrets Manager
  for identity, access, and configuration management.
• Integrate and optimize vector search and retrieval using
  Pinecone
  .
• Build and manage asynchronous data pipelines and audio-to-text processing using
  Deepgram
  .
• Develop and maintain backend persistence layers with
  AWS RDS
  and
  S3
  for structured and unstructured data.
• Configure and optimize load balancing and network routing via
  AWS ALB
  and
  NLB
  .
• Ensure system reliability, observability, and cost optimization through monitoring, autoscaling, and container best practices.
• Collaborate with the AI team to experiment with new architectures, LLM tools, and prompt engineering techniques.
• Write clean, testable, and maintainable code across the stack (Python, , or Go preferred).

Required Skills & Experience

• Proven experience in full-stack development with strong backend focus.
• Hands-on experience with
  LangChain
  and
  LangGraph
  for agentic AI and orchestration.
• Deep understanding of
  OpenAI APIs (GPT, Whisper, Embeddings)
  and model integration patterns.
• Strong command of
  AWS services
  , including ECS, EKS, Cognito, IAM, S3, RDS, Secrets Manager, ALB, and NLB.
• Experience managing infrastructure-as-code (Terraform or CloudFormation).
• Familiarity with
  vector databases
  (Pinecone, Weaviate, or Milvus).
• Strong understanding of
  containerization
  (Docker, Kubernetes).
• Experience integrating speech-to-text or audio AI using
  Deepgram
  or similar.
• Proficiency with RESTful and GraphQL APIs, microservices, and serverless design.
• Solid grounding in CI/CD workflows and version control (Git, GitHub Actions, or AWS CodePipeline).

Nice to Have

• Frontend experience with React or
• Exposure to
  LangSmith
  ,
  OpenAI Assistants API
  , or
  Retrieval-Augmented Generation (RAG)
  systems.
• Knowledge of observability stacks (Prometheus, Grafana, CloudWatch).
• Experience with data security and compliance (SOC2, GDPR, HIPAA).
• Experience leading a team of 3-5 engineers
• Ability to travel to US/EU as needed
• Enough fluency in English to present capabilites at conferences.

Ideal Candidate

You're an engineer who thrives at the intersection of
AI, cloud architecture, and full-stack development
. You enjoy building intelligent systems that scale, designing elegant API interfaces, and turning theoretical models into robust, real-world products. You're comfortable operating independently in fast-moving environments and collaborating cross-functionally to deliver impact.