Experience
4 - 8 yrs
Job Location
Noida, India
Vacancy
1
Designation
Lead Machine Learning Engineer
Job Type
Not specified
Job Description
Gen AI - Lead
Location: Noida, UP, India
Company: Iris Software
Job Description Role Overview
We are looking for an experienced Lead Engineer (8 - 10 Years) with strong expertise in Python, AWS Cloud, Generative AI, and hands-on experience in RAG (Retrieval Augmented Generation), Agentic workflows, and building LLM-powered applications. The ideal candidate will lead design, architecture, and development of scalable AI solutions, mentor the team, and collaborate closely with product and architecture teams.
Key Responsibilities: - Architecture, Design Technical Leadership
- Lead end-to-end design and development of GenAI-powered applications.
- Ability to understand and translate customer requirement into scalable AI architectures and meaningful design leveraging cloud services
- Drive adoption of LLM orchestration frameworks (LangChain 1.0, LangGraph, OpenAI tools, custom agents).
- Keep pace with technological evolution in Gen AI space, explore and set up PoC for better solutions
- Generative AI Development
- Build RAG pipelines using vector databases, embeddings, and document indexing.
- Design and implement Agentic workflows
- Implement vector search using PGVector, FAISS etc.
- Create embedding pipelines, chunking strategies, metadata tagging, and retrieval optimizations.
- MCP
- Python Cloud
- Build backend services, API layers, and model-serving components in Python (Flask).
- Understanding of AWS services such as ECS, API Gateway, S3, Bedrock, CloudWatch, SageMaker.
- Performance and Security as first principles
- Collaboration
- Lead a small team of engineers, conduct code reviews and design reviews.
- Work with cross-functional teams Product, Architecture, Security, Data Engineering.
- Ensure best practices in coding, testing, observability, and DevOps.
- Strong proficiency in Python (Flask, REST, async programming).
- Deep hands-on experience with Generative AI and LLM-based applications.
- Expertise in RAG development, embeddings, vector databases.
- Experience with Agent frameworks (LangChain 1.0, LangGraph, ReAct, OpenAI Assistants, or custom agents).
- Strong understanding of AWS/Azure/GCP Cloud architecture.
- Experience with API development, microservices, and event-driven systems.
- Familiarity with CI/CD pipelines, Docker, GitLab/GitHub Actions.
- Data Science and Machine Learning - Data Science and Machine Learning - Gen AI
- Programming Language - Python - Flask
- Beh - Communication
- DevOps/Configuration Mgmt - DevOps/Configuration Mgmt - GitLab,Github, Bitbucket
- Cloud - AWS - AWS S3, S3 glacier, AWS EBS
- Data Science and Machine Learning - Data Science and Machine Learning - AWS Sagemaker
- Cloud - AWS - ECS
- Development Tools and Management - Development Tools and Management - CI/CD
No Referrers Available
There are currently no referrers available for this job. You can still apply, will let you know once there is any referrer available.