Position Summary :

We are seeking a Full Stack AI Developer to design, build, and deploy AI-powered planning solutions that combine modern web applications with large language models and retrieval-based intelligence.

The role spans backend API development, frontend user experiences, AI/LLM orchestration, data retrieval, and production deployment.

The ideal candidate can turn planning and workflow requirements into secure, reliable, observable, and maintainable applications.

Key Responsibilities :

- Design and develop backend services and APIs using Python and FastAPI.

- Build responsive, user-friendly frontend applications using React or Angular with TypeScript.

- Integrate foundation models and generative AI capabilities using AWS Bedrock.

- Develop RAG pipelines, embedding workflows, semantic retrieval, and grounded AI responses using suitable vector search technologies.

- Implement multi-step AI workflows and agent orchestration using LangGraph or comparable frameworks.

- Connect AI services to enterprise data sources, SQL/NoSQL databases, and internal APIs while applying appropriate access controls.

- Instrument AI applications with Langfuse or similar tools to trace requests and monitor latency, token usage, failures, and output quality.

- Package services using Docker and deploy them to Kubernetes or Amazon ECS environments.

- Build and maintain CI/CD pipelines, automated tests, and deployment processes.

- Collaborate with product, planning, data, cloud, and security teams to translate business needs into production-ready solutions.

- Troubleshoot application and AI pipeline issues; improve reliability, performance, security, and cost efficiency.

- Document architecture, APIs, prompts, retrieval strategies, operational procedures, and technical decisions.

Required Technical Skills :

- Strong Python development skills and experience building backend services with FastAPI or an equivalent framework.

- Frontend development experience with React or Angular, TypeScript, and modern JavaScript.

- Practical experience integrating LLMs, including AWS Bedrock or comparable managed model platforms.

- Understanding of prompt engineering, structured model outputs, and safe, reliable LLM integration patterns.

- Experience with RAG concepts, embedding models, chunking, retrieval, semantic search, and evaluation of retrieved context.

- Experience with a vector database or search platform such as Pinecone, OpenSearch, Weaviate, or an equivalent solution.

- Knowledge of SQL and NoSQL databases, data modeling, and API integration.

- Experience using Docker and deploying applications through Kubernetes, Amazon ECS, or similar container platforms.

- Familiarity with Git, CI/CD pipelines, automated testing, and production support practices.

- Strong debugging, problem-solving, communication, and collaborative development skills.

Preferred Qualifications :

- Hands-on experience with LangGraph or other frameworks for agentic and multi-step AI workflows.

- Experience with Langfuse or comparable LLM observability, tracing, and evaluation tools.

- Experience deploying AI-enabled applications on AWS and working with cloud IAM, secrets, logging, and monitoring.

- Understanding of LLM evaluation, hallucination reduction, grounding, guardrails, latency optimization, and token-cost management.

- Experience building planning, forecasting, scheduling, decision-support, or enterprise workflow solutions.

- Knowledge of application security, privacy, and responsible handling of sensitive business data.

What We Are Looking For :

We are looking for a hands-on engineer who can work across the full application stack and contribute to the AI solution lifecycle - from API and interface development to retrieval, model orchestration, deployment, and observability.

The ideal candidate combines strong software engineering fundamentals with practical judgment about where AI adds value, and can deliver solutions that are testable, secure, maintainable, and useful to business users.

Technology Stack :

- Backend : Python, FastAPI

- Frontend : React or Angular, TypeScript

- AI/LLM : AWS Bedrock, LangGraph, RAG pipelines, embeddings

- Observability : Langfuse or similar LLM observability tools

- Infrastructure : Docker, Kubernetes or Amazon ECS, CI/CD

- Data : Pinecone, OpenSearch, Weaviate or similar vector databases; SQL/NoSQL

Education & Experience :

Relevant professional experience in full stack software development, AI/LLM application development, or a related field is expected.

A degree in Computer Science, Information Technology, Engineering, or equivalent practical experience is preferred.

Years of experience and any role-specific mandatory qualifications should be confirmed before publishing this draft.