Full Stack Engineer (AI Tools)

Role: Full Stack Engineer (AI Tools)
Position Type: Full-Time Contract (40hrs/week)
Contract Duration: Long Term (with a possibility of contract to hire)
Work Schedule: 8 hours/day (Mon-Fri)
Location: Hybrid - 1x day onsite in Bangalore or Chennai

About the Role

We are seeking a Full Stack Engineer to design, build, and ship AI-powered applications and tools that support key business functions across Product, Sales, Finance, Marketing, Customer Success, and Engineering. You will work end to end from frontend and API design through backend services, GenAI integration, deployment, and monitoring turning business problems into reliable, production-grade tools that people actually use.

This role is ideal for a versatile engineer who enjoys owning features from idea to production, is comfortable across the stack, and wants to build with modern GenAI capabilities at the core of the product.

What You Will Do

Full Stack Application Development

• Build responsive, intuitive frontends (Angular/React/TypeScript) and robust backend services (Python/FastAPI or Node.js) for internal and customer-facing AI tools.

• Design and implement clean, well-documented APIs that connect AI capabilities to business workflows.

• Own features end to end: requirements, design, implementation, testing, deployment, and iteration.

GenAI and AI Tooling

• Build GenAI applications using OpenAI APIs, embeddings, vector search, and RAG.

• Implement LLM orchestration, tool/function calling, and lightweight agentic workflows.

• Develop prompt engineering patterns and automated evaluation frameworks to measure and improve quality.

• Integrate AI features into products in ways that are reliable, cost-aware, and safe.

Cloud and Data Engineering

• Deploy and operate services on AWS (Lambda, S3, ECS/containers, API Gateway, Agentcore).

• Build and optimize data and feature pipelines using Python, SQL, and where relevant Databricks, Spark, and Delta Lake.

• Ensure data quality, observability, and documentation across the systems you build.

Enterprise System Integrations

• Build and maintain integrations with enterprise systems such as Salesforce (SFDC), Oracle Fusion, Oracle Service Cloud, and PeopleSoft.

• Support real-time and batch workflows that enhance CRM, sales, customer service, and marketing operations.

Productionization, Reliability, and Support

• Implement monitoring, logging, and alerting for application health, model drift, and prompt performance.

• Provide L2/L3 support for the tools and pipelines you build.

• Contribute to root cause analysis and build preventive measures for long-term stability.

Cross-Functional Collaboration

• Partner with Product, Engineering, and business stakeholders to translate challenges into working tools with clear ROI.

• Communicate technical concepts clearly to non-technical audiences.

• Support adoption through demos, documentation, and enablement.

Required Skills

Generalist Strengths

• Ability to design end-to-end solutions spanning UI, APIs, data, models, and automation in close collaboration with the end users around the business.

• Comfort working across ambiguity and owning delivery of complete features and delivering at speed.

• Strong communication and collaboration skills.

• Ability to manage multiple workstreams and deliver with limited direction.

Core Technical Skills

• Strong programming skills in Python and JavaScript/TypeScript using agentic coding tools like Claude or Codex to accelerate development.

• Experience building full stack applications (frontend frameworks such as Angular/React; backend frameworks such as FastAPI, Flask, or Node.js).

• Hands-on experience with OpenAI APIs, LLM workflows, RAG, and prompt engineering.

• Solid API design skills (REST; GraphQL a plus) and comfort integrating third-party services.

• Strong SQL skills and experience working with large datasets.

• Experience deploying on AWS (S3, Lambda, and container or serverless compute).

• Familiarity with databases and cloud data warehouses (e.g., Postgres/pgvector, Redshift, Snowflake).

Nice to Have

• Experience with vector databases (Pinecone, Weaviate, pgvector) and LLM frameworks (LangChain, LlamaIndex).

• Experience with CI/CD, Docker, and infrastructure-as-code.

• Experience with MLflow or other MLOps/LLMOps tooling.

• Experience building customer-facing or enterprise GenAI applications.

• Familiarity with Databricks, Spark, and Delta Lake.

Education

• Bachelor's degree in Computer Science, Engineering, or a related technical field is required.

• Equivalent practical experience will be considered.