Application Support Engineer

• *Project Role :** Application Support Engineer

• *Project Role Description :** Act as software detectives, provide a dynamic service identifying and solving issues within multiple components of critical business systems.

• *Must have skills :** AI Agents \& Workflow Integration

• *Good to have skills :** NA

Minimum **3** year(s) of experience is required

• *Educational Qualification :** 15 years full time education

Role Summary

We are seeking a Generative AI Engineer with strong hands\-on experience in Databricks and AWS to design, build, and scale LLM\-powered, agentic AI solutions for enterprise\-grade use cases. The role involves developing intelligent agents, RAG pipelines, and AI\-driven data products that are production\-ready, scalable, secure, and cost\-efficient.

Key Responsibilities

Design and develop GenAI and Agentic AI solutions using LLMs for enterprise use cases

Build RAG pipelines leveraging structured and unstructured data (documents, PDFs, logs, metadata)

Implement AI agents and workflows using AWS Agent Core / Bedrock and orchestration frameworks

Develop GenAI applications on Databricksusing notebooks, jobs, and scalable compute

Integrate GenAI solutions with data lakes, lakehouse, and enterprise systems

Optimize solutions for latency, accuracy, cost, and scalability

Implement prompt engineering, prompt chaining, and guardrails

Work closely with data engineers, architects, and business stakeholders to translate requirements into AI\-driven solutions

Contribute to AI governance, observability, and responsible AI practices

Support deployment, monitoring, and continuous improvement of GenAI systems in production

Must\-Have Technical Skills

GenAI / LLM

Hands\-on experience with LLMs (Claude, OpenAI, Llama, etc.)

Strong knowledge of RAG architectures, embeddings, vector search

Experience building agentic workflows(planning, tool use, reasoning loops)

Prompt engineering, few\-shot / chain\-of\-thought techniques

Databricks

Strong experience with Databricks Lakehouse

PySpark, SQL, Delta Lake

Databricks workflows / jobs

MLflow for experimentation and model tracking

Unity Catalog (preferred)

AWS

AWS Bedrock (models, inference, agents)

AWS Agent Core or agent orchestration patterns

Lambda, API Gateway, S3

IAM, security best practices for AI workloads

Programming

Python (advanced)

SQL

APIs and microservices integration

Good\-to\-Have Skills

LangChain / LangGraph / DSPy or similar frameworks

Vector databases (OpenSearch, FAISS, Pinecone, etc.)

LLMOps / MLOps exposure

CI/CD for AI applications

Knowledge of AI governance, compliance, and security

Experience working in client\-facing / consulting environments

15 years full time education