Senior Technical Lead - Java, Microservices, React.js

Job Summary

We are looking for a Senior Full‑Stack AI Engineer with strong software engineering fundamentals, deep Generative AI experience, and hands‑on UI development using React. The ideal candidate will build end‑to‑end AI‑powered applications, combining agentic AI systems with modern, scalable user interfaces.

This role follows an AI‑first approach—LLMs and agents are the default solution for intelligence and automation—while also owning frontend and backend application development for user‑facing AI experiences.

Key Responsibilities

Key Responsibilities Frontend Development

• Design and build modern, responsive user interfaces using React/Angular.

• Develop reusable UI components and application layouts for AI‑driven workflows.

• Integrate frontend applications with backend AI services via secure REST APIs.

• Collaborate with UX and product teams to deliver intuitive AI‑powered user experiences.

--- AI‑First System Design & Software Engineering

• Apply strong software engineering principles to design, build, test, deploy, and operate AI‑powered systems.

• Architect clean, scalable, and maintainable services using microservices and distributed system design patterns.

• Own solutions end‑to‑end, ensuring reliability, observability, security, and maintainability in production.

• Make informed engineering trade‑offs around scalability, latency, cost, and fault tolerance.

--- Generative AI & Retrieval‑Augmented Generation (RAG)

• Design and implement LLM‑based solutions for real‑world, production use cases.

• Apply deep hands‑on expertise in:

• Prompt engineering

• Chunking strategies for unstructured data

• Embeddings and vector databases

• Retrieval‑Augmented Generation (RAG)

• Graph RAG (knowledge graphs combined with vector search).

• Ensure AI systems are robust, explainable, and production‑ready.

--- Agentic AI & Workflow Automation

• Build Agentic AI systems capable of planning, reasoning, and executing multi‑step workflows.

• Implement tool and function calling, context management, and memory strategies for agents.

• Design systems where agents orchestrate workflows and LLMs act as reasoning and decision layers.

• Identify opportunities to replace manual or rule‑based processes with AI‑driven automation.

--- Cloud‑Native AI Platforms & AWS

• Build and deploy AI services on AWS using cloud‑native patterns.

• Work hands‑on with AWS services such as:

• EC2, Lambda, ECS, EKS

• DynamoDB, RDS (PostgreSQL/MySQL), MongoDB

• IAM, VPC, S3, EBS, CloudFront, Route 53.

• Leverage AWS Bedrock (Agents, Knowledge Bases) and Amazon Sage Maker to operationalize AI solutions.

--- Containers, DevOps & CI/CD

• Containerize AI services using Docker and deploy using Kubernetes (EKS).

• Integrate services into CI/CD pipelines using GitHub or GitLab.

• Manage infrastructure using Infrastructure as Code (Terraform).

Ensure stable, repeatable deployments in Linux environments

Skill Requirements

Required Skills & Qualifications

• 5+ years of experience in Software Engineering or AI Engineering.

• Strong software engineering skills with proven experience building production systems.

• Strong programming experience in Python.

• Hands‑on experience with:

• Generative AI and Large Language Models

• RAG pipelines, embeddings, and vector databases

• Agentic AI workflows and systems.

• Solid understanding of:

• System design

• Microservices and distributed systems.

• Experience deploying and operating systems on AWS.

Comfortable working in Agile environments and Linux systems

Other Requirements

Good to Have

• Knowledge graph experience

• MLOps exposure

Experience working within enterprise AI governance frameworks