Senior AI Engineer, AI Systems (India)

Ovii's Interpretation of the Role

Senior AI Engineer responsible for designing, building, and scaling LLM‑driven agent and retrieval systems that enforce enterprise AI governance policies.

Role Snapshot

• Design AI agent architectures for policy‑driven action
• Build telemetry, monitoring, and analytics for agent behavior
• Create retrieval‑augmented knowledge systems
• Define evaluation frameworks to verify governance alignment
• Set platform‑wide engineering standards for AI systems

Must-Have Requirements

• Production LLM‑based AI applications
• Agent architecture design (tool use, planning, multi‑step reasoning)
• Evaluation framework design and execution
• Prompt engineering / output validation
• Distributed systems, data pipelines, APIs
• Observability and monitoring for AI
• Retrieval‑augmented generation and hybrid retrieval
• Telemetry and analytics infrastructure
• Production AI/ML system development
• LLM‑based application delivery
• Agent architecture implementation
• Evaluation mindset and framework creation
• Behavioral shaping (prompt, policy constraints)
• Systems engineering for distributed pipelines
• Monitoring/observability for AI

Nice-to-Have Signals

• Research background or publications in LLM evaluation, alignment, or AI safety
• Red‑team or adversarial evaluation experience
• Multi‑agent system experience
• Open‑source ML or evaluation infrastructure contributions
• Familiarity with AI governance, compliance, or risk‑management domains
• Research publications in LLM evaluation or AI safety
• Red‑team or adversarial testing
• Multi‑agent system design
• AI governance domain familiarity
• Open‑source contributions

Work Setup

• Location: India
• Work mode: REMOTE
• Remote scope: COUNTRY_RESTRICTED
• Remote countries: India
• Timezone: Supports EST/CST/PST (choice)
• Employment type: Full-Time

Eligibility Gates

• Visa sponsorship: unknown

Not Specified in JD

• Visa sponsorship
• Security clearance
• Travel requirements

What You'll Likely Work On

• Design and implement agent architectures that reason about governance policies and act within defined constraints
• Instrument agents to expose auditable behavior and build analytics pipelines for enterprise‑scale verification
• Develop behavioral configuration systems that encode organizational policies into AI actions
• Architect evaluation frameworks that measure alignment between agent behavior and governance intent
• Create retrieval and context services that surface relevant governance knowledge using hybrid semantic and structured search
• Contribute to the broader AI platform architecture and translate governance intelligence into reliable product features
• Establish engineering standards, best practices, and observability tooling for AI system development

Good Fit If You Have

• Research publications on LLM evaluation, alignment, or AI safety
• Experience with red‑team or adversarial evaluation of AI models
• Background in multi‑agent system design
• Familiarity with AI governance, compliance, or risk‑management domains
• Contributions to open‑source ML or evaluation infrastructure