Responsibilities

- Build features and services across the AI stack orchestration retrieval/grounding prompt/agent logic
- evaluation/guardrails serving and observability
- Implement robust data processing and integration pipelines to enable high quality AI applications and analytics
- Contribute to design docs code reviews testing and operational playbooks to ensure reliability maintainability
- and resilience
- Partner with product and business stakeholders to define requirements iterate quickly and measure outcomes
- using clear success metrics
- Instrument telemetry and evaluation to monitor quality safety latency and cost improve performance
- based on data
- Follow responsible AI practices for security privacy compliance and safety in collaboration with governance
- teams
- Participate in on call and incident response rotations as appropriate drive post incident improvements
- Share learnings via demos and documentation contribute to AI literacy and enablement across the org

- Qualifications
- BS/MS in Computer Science or a related field or equivalent experience
- Practical software engineering experience building backend services APIs or data intensive applications
- strong foundations in algorithms data structures and systems
- Exposure to or handson experience with LLM application concepts such as retrieval grounding prompt agent
- design functiontool use evaluation safety guardrails and costlatency optimization
- Proficiency with modern software delivery practices version control CICD testing observability familiarity
- with cloud native services and containerization
- Ability to collaborate with product and business partners robust written and verbal communication skills




- Bias to ship learn and iterate comfortable working in fast evolving technology areas with incomplete
- information
- For Senior level demonstrated ownership of services or platform components endtoend delivery of crossservice
- initiatives and contributions to reliabilitySLOs and operational excellence

This is the sumary

Senior AI Engineer Applied AI Technical Competencies

1 Agentic Workflows Memory Systems

Stateful Orchestration Building and debugging productiongrade cyclic multiagent workflows and state machines

Context Memory Engineering Implementing multilayered memory architectures including shortterm memory for active turn execution longterm memory for crosssession state persistence and episodic summarization to manage token context windows

Tool Call Management Designing dependable functioncalling patterns equipped with automated retry logic and selfcorrection handlers

2 Data Retrieval Infrastructure

Vector Relational Storage Managing relational metadata schemas and executing optimized semantic vector similarity searches inside a combined relational database layer

Document Persistence Utilizing documentstore databases to store unstructured execution payloads dynamic agent states and raw chat logs

Hybrid RAG Pipelines Combining relationalexactmatch queries with vectorspace searches for highprecision retrieval

3 Production Reliability Performance

Granular Tracing Instrumenting endtoend tracing to monitor agent execution steps debug nondeterministic loops and track token costs

Automated Evals Creating programmatic evaluation testing and scoring frameworks to benchmark agent accuracy before production deployment

Core Backend Development Writing clean concurrent asynchronous Python code to handle high throughput foundation model APIs

📌 AI Engineer - Python (Pune)
🏢 Cognizant
📍 Pune