The Role
Design and deploy agentic generative AI and multi-agent automation systems using LLMs, RAG, vector DBs, and orchestration frameworks. Implement LLM governance, build backend APIs (FastAPI/Flask), create demos, contribute to MLOps (CI/CD, Docker, Kubernetes, monitoring), and develop ML models (NLP, computer vision, predictive analytics) while collaborating with product, architecture, and compliance teams.
Summary Generated by Built In
• Design and deploy agentic generative AI solutions leveraging LLMs, RAG pipelines, context engineering,
and REST APIs.
• Architect and build multi-agent automation systems using frameworks such as LangGraph or similar
orchestration platforms
• Implement LLM governance architecture including prompt drift detection, auditability, and safety policies
to ensure regulatory compliance.
• Develop and integrate vector database solutions for semantic search and retrieval-augmented
generation.
• Collaborate cross-functionally with AI architects, product managers, and compliance teams to accelerate
AI adoption across business units.
• Develop APIs using FastAPI/Flask and build interactive demos for stakeholder showcases.
• Contribute to MLOps practices including CI/CD pipelines, model monitoring, and deployment automation.
• Conduct research experiments to enhance model performance, reliability, and fairness.
• Build and maintain ML models for domain-specific tasks such as NLP, computer vision, and predictive
analytics.
Requirements
• Programming: Proficiency in Python; working knowledge of SQL and Java.
• GenAI & LLMs: Deep expertise in LLMs, RAG, prompt engineering, fine-tuning, and model governance.
• Frameworks: LangChain,
• APIs & Backend: FastAPI, Flask, REST API design.
• Databases: Vector databases (Milvus, PGVector), PostGRESQL.
• Cloud & MLOps: Azure AI Foundry; Docker, Kubernetes, CI/CD pipelines.
• Visualization & UI: Streamlit, basic UI/UX design principles.
Skills Required
- Proficiency in Python
- Working knowledge of SQL
- Working knowledge of Java
- Deep expertise in LLMs, RAG, prompt engineering, fine-tuning, and model governance
- Experience with multi-agent orchestration frameworks (LangGraph or similar)
- Experience with LangChain
- API and backend development using FastAPI or Flask and REST API design
- Experience with vector databases (Milvus, PGVector) and PostgreSQL
- Experience with Azure AI Foundry
- Containerization and orchestration: Docker and Kubernetes
- CI/CD pipeline experience and MLOps practices including model monitoring and deployment automation
- Experience building interactive demos and using Streamlit; basic UI/UX design principles
- Experience conducting research experiments to improve model performance, reliability, and fairness
- Experience building ML models for domain-specific tasks such as NLP, computer vision, and predictive analytics
- Ability to implement LLM governance features (prompt drift detection, auditability, safety policies) to ensure compliance
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
Marketscope is a technology company specializing in the development and integration of Advanced Driver Assistance Systems (ADAS) and the scaling of production-grade AI/ML applications. The company focuses on AI platform engineering and product stacks, targeting strategic enterprise accounts and government sales, particularly within the Indian market, while expanding its reach into new international industries.
