Senior Gen AI Developer

Position Summary -
The Senior Generative AI Developer will be a key contributor responsible for the design
development testing and deployment of production-grade Generative AI applications. This hands-
on role requires deep expertise in modern software development practices proficiency in Large
Language Models (LLMs) and the ability to integrate sophisticated AI capabilities into existing
enterprise software systems. The ideal candidate will mentor junior team members and drive
technical excellence in GenAI implementation.

Key Responsibilities and Duties -
Complete Hands-on in developing Agentic AI production scalable experience is mandatory.

Code Development: Write clean efficient and well-documented code primarily in Python to
build Generative AI features microservices and APIs.

Prompt Engineering: Design implement and rigorously test advanced Prompt Engineering
techniques (e.g. Chain-of-Thought few-shot learning) to maximize model performance and
adherence to task specifications.

RAG System Development: Architect and implement high-performance Retrieval-Augmented
Generation (RAG) pipelines including data chunking embedding generation vector
database interaction (e.g. Pinecone ChromaDB) and context retrieval optimization.

Model Integration: Integrate customize and deploy both commercial (OpenAI Anthropic)
and open-source (Llama Mistral) LLMs via APIs local inference or cloud-based services
(e.g. AWS Bedrock Azure OpenAI).

Model Fine-Tuning (LoRA): Execute model fine-tuning and adaptation techniques such as
LoRA (Low-Rank Adaptation) and QLoRA on domain-specific datasets to improve accuracy
and reduce model size.

Ability to work in a dynamic and high-pressure environment with a solution mind-set

Documentation: Create and maintain detailed technical documentation for all developed
code APIs and infrastructure configurations.



Technical Expertise -

End-to-End ML/DL Expertise: Full-stack mastery of Machine Learning and Deep Learning
ranging from traditional frameworks (Scikit-Learn XGBoost) to advanced computer vision
(OpenCV TensorFlow) and privacy-centric architectures like Federated and Distributed
Learning.

Advanced Data & Vector Engineering: Expert in building scalable ETL pipelines and hybrid
search systems using high-performance vector databases (ChromaDB OpenSearchMilvus
Pinecone) and traditional stores (PostgreSQL Redis) supported by robust model
explainability (SHAP LIME).

Production Deployment & Observability: Proven track record in shipping GDPR-compliant
applications using Docker Azure and Linux with integrated telemetry and visualization via
Azure Live Metrics Metabase and Seaborn

Hands-on experience building multi-agent systems using frameworks like LangGraph
CrewAI or Autogen. You should be comfortable designing "Plan-and-Execute" loops.

Experience: 5 years of experience in software development with at least 2 years focused
specifically on Generative AI NLP or applied Machine Learning.

Experience building and exposing APIs/tools for AI or agent-based systems

Familiarity with Model Context Protocol (MCP) or similar frameworks for tool integration

Ability to design and manage structured input/output interfaces for LLM-driven workflows

Programming Mastery: Expert proficiency in Python and its ecosystem (Pandas NumPy)
with a strong foundation in Object-Oriented Programming (OOP) principles.

GenAI Frameworks: Hands-on experience with key GenAI libraries and frameworks such as
LangChain LlamaIndex Hugging Face Transformers or PyTorch/TensorFlow.

Data &Databases: Experience working with both traditional databases (SQL NoSQL) and
specialized Vector Databases.

Cloud & Deployment: Experience with cloud computing platforms (AWS Azure or GCP) and
familiarity with CI/CD tools Docker and Kubernetes for application deployment.

Required Skills:

llmragnlpgenaimachine learninglanggraphcrewai