About us

Job Description of : AI Engineer

Job Title : Deputy Manager I/II

Department : Information Technology

Reports To : Deputy Mangaer I/II

Experience : 3 to 8 years

Preferred Qualification : BE/ B Tech/ MCA

Required Qualification : BE/ B Tech/ MCA

1) Proven experience on AI and software engineering with deep fluency in Python, modern AI frameworks, vector and graph databases.
2) Deep expertise in building and deploying production-grade AI systems, workflows and models 

Core Competencies :

1) 	Advanced RAG Architectures: Expertise in building and optimizing Retrieval-Augmented Generation systems. This includes advanced chunking strategies, multi-stage retrieval, re-ranking, and hybrid search.
2) 	Agentic Workflows & Tool Use: Deep experience designing multi-agent systems, function calling, stateful orchestration frameworks, and error-handling loops.
3) 	Evaluation & Guardrails: Proficiency in implementing systematic LLM evaluation frameworks (e.g., Ragas, TruLens) and safety/compliance guardrails (e.g., NeMo Guardrails, Llama Guard) to control hallucination and data leakage.
4) 	Data Pipelines & Vector Databases: Expertise in managing high-throughput data pipelines and unstructured data processing. Advanced knowledge of vector storage and indexing (e.g., Pinecone, Milvus, Qdrant, pgvector).
5) 	Enterprise Integration & Security: Ability to securely hook AI applications into legacy enterprise architectures, including REST/gRPC APIs, IAM/OAuth systems, and VPC networks.
6) 	Cloud & Containerization: Fluency with containerized infrastructure (Docker, Kubernetes) and enterprise cloud platforms (AWS, GCP, Azure) to deploy scalable, highly available workloads.
7) 	Production-Grade Software Engineering: Writing clean, modular, and asynchronous Python code adhering to strict CI/CD pipelines, automated testing, and logging/observability standards (e.g., OpenTelemetry, Arize, LangSmith).
8) 	Model Performance Monitoring. Expertise in tracking and measuring Core System Metrics like Tracking latency-per-token, time-to-first-token (TTFT), token consumption patterns, system throughput, and error rates (e.g., rate limits, API timeouts).
9) 	Production Data and Model Drift Monitoring and Management: Past proven expertise in detecting shifts in user behaviour, intent, or input format. Monitoring the underlying data source, the data distribution drifts. Evaluating changes in model behaviour over time, especially when using third-party APIs 
10) 	Explainability & Lineage: Past experience in showcasing deep transparency in AI decisions making process and logging clear logical reasoning chain. 

Functional Competencies :

Financial Market

Job Purpose :

The successful candidate would bridge the gap between cutting-edge AI platform capabilities and real-world business execution of Enterprise AI use cases. Candidate will be a hands-on full stack AI engineer who embeds shoulder-to-shoulder with CCIL core business teams right from initial discovery and building production scale AI systems to scaling robust agentic architectures and RAG (Retrieval-Augmented Generation) pipelines in production. 

Area of Operations :

AI and software engineering

Key Responsibility :

1) 	Advanced RAG Architectures: Expertise in building and optimizing Retrieval-Augmented Generation systems. This includes advanced chunking strategies, multi-stage retrieval, re-ranking, and hybrid search.
2) 	Agentic Workflows & Tool Use: Deep experience designing multi-agent systems, function calling, stateful orchestration frameworks, and error-handling loops.
3) 	Evaluation & Guardrails: Proficiency in implementing systematic LLM evaluation frameworks (e.g., Ragas, TruLens) and safety/compliance guardrails (e.g., NeMo Guardrails, Llama Guard) to control hallucination and data leakage.
4) 	Data Pipelines & Vector Databases: Expertise in managing high-throughput data pipelines and unstructured data processing. Advanced knowledge of vector storage and indexing (e.g., Pinecone, Milvus, Qdrant, pgvector).
5) 	Enterprise Integration & Security: Ability to securely hook AI applications into legacy enterprise architectures, including REST/gRPC APIs, IAM/OAuth systems, and VPC networks.
6) 	Cloud & Containerization: Fluency with containerized infrastructure (Docker, Kubernetes) and enterprise cloud platforms (AWS, GCP, Azure) to deploy scalable, highly available workloads.
7) 	Production-Grade Software Engineering: Writing clean, modular, and asynchronous Python code adhering to strict CI/CD pipelines, automated testing, and logging/observability standards (e.g., OpenTelemetry, Arize, LangSmith).
8) 	Model Performance Monitoring. Expertise in tracking and measuring Core System Metrics like Tracking latency-per-token, time-to-first-token (TTFT), token consumption patterns, system throughput, and error rates (e.g., rate limits, API timeouts).
9) 	Production Data and Model Drift Monitoring and Management: Past proven expertise in detecting shifts in user behaviour, intent, or input format. Monitoring the underlying data source, the data distribution drifts. Evaluating changes in model behaviour over time, especially when using third-party APIs 
10) 	Explainability & Lineage: Past experience in showcasing deep transparency in AI decisions making process and logging clear logical reasoning chain. 

Any Other Requirement :

1) 	Should be a good team player.
2) 	Should be excellent in communication and data analytics
3) 	Would be required to work with multiple projects / teams concurrently